diff --git a/notebooks/en/fine_tuning_vlm_trl.ipynb b/notebooks/en/fine_tuning_vlm_trl.ipynb
index 4981a362..29b5851d 100644
--- a/notebooks/en/fine_tuning_vlm_trl.ipynb
+++ b/notebooks/en/fine_tuning_vlm_trl.ipynb
@@ -1,4357 +1,4367 @@
{
- "cells": [
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "vKadZFQ2IdJb"
- },
- "source": [
- "# Fine-Tuning a Vision Language Model (Qwen2-VL-7B) with the Hugging Face Ecosystem (TRL)\n",
- "\n",
- "\n",
- "\n",
- "_Authored by: [Sergio Paniego](https://github.com/sergiopaniego)_\n",
- "\n"
- ]
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "vKadZFQ2IdJb"
+ },
+ "source": [
+ "# Fine-Tuning a Vision Language Model (Qwen2-VL-7B) with the Hugging Face Ecosystem (TRL)\n",
+ "\n",
+ "\n",
+ "\n",
+ "_Authored by: [Sergio Paniego](https://github.com/sergiopaniego)_\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "JATmSI8mcyW2"
+ },
+ "source": [
+ "🚨 **WARNING**: This notebook is resource-intensive and requires substantial computational power. If you’re running this in Colab, it will utilize an A100 GPU.\n",
+ "\n",
+ "In this recipe, we’ll demonstrate how to fine-tune a [Vision Language Model (VLM)](https://huggingface.co/blog/vlms) using the Hugging Face ecosystem, specifically with the [Transformer Reinforcement Learning library (TRL)](https://huggingface.co/docs/trl/index).\n",
+ "\n",
+ "**🌟 Model & Dataset Overview**\n",
+ "\n",
+ "We’ll be fine-tuning the [Qwen2-VL-7B](https://qwenlm.github.io/blog/qwen2-vl/) model on the [ChartQA](https://huggingface.co/datasets/HuggingFaceM4/ChartQA) dataset. This dataset includes images of various chart types paired with question-answer pairs—ideal for enhancing the model's visual question-answering capabilities.\n",
+ "\n",
+ "**📖 Additional Resources**\n",
+ "\n",
+ "If you’re interested in more VLM applications, check out:\n",
+ "- [Multimodal Retrieval-Augmented Generation (RAG) Recipe](https://huggingface.co/learn/cookbook/multimodal_rag_using_document_retrieval_and_vlms): where I guide you through building a RAG system using Document Retrieval (ColPali) and Vision Language Models (VLMs).\n",
+ "- [Phil Schmid's tutorial](https://www.philschmid.de/fine-tune-multimodal-llms-with-trl): an excellent deep dive into fine-tuning multimodal LLMs with TRL.\n",
+ "- [Merve Noyan's **smol-vision** repository](https://github.com/merveenoyan/smol-vision/tree/main): a collection of engaging notebooks on cutting-edge vision and multimodal AI topics.\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "QoD6dxPeXDKR"
+ },
+ "source": [
+ ""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "gSHmDKNFoqjC"
+ },
+ "source": [
+ "## 1. Install Dependencies\n",
+ "\n",
+ "Let’s start by installing the essential libraries we’ll need for fine-tuning! 🚀\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
},
+ "id": "GCMhPmFdIGSb",
+ "outputId": "b08f3edd-03e2-42af-a075-04dafa232c66"
+ },
+ "outputs": [
{
- "cell_type": "markdown",
- "metadata": {
- "id": "JATmSI8mcyW2"
- },
- "source": [
- "🚨 **WARNING**: This notebook is resource-intensive and requires substantial computational power. If you’re running this in Colab, it will utilize an A100 GPU.\n",
- "\n",
- "In this recipe, we’ll demonstrate how to fine-tune a [Vision Language Model (VLM)](https://huggingface.co/blog/vlms) using the Hugging Face ecosystem, specifically with the [Transformer Reinforcement Learning library (TRL)](https://huggingface.co/docs/trl/index).\n",
- "\n",
- "**🌟 Model & Dataset Overview**\n",
- "\n",
- "We’ll be fine-tuning the [Qwen2-VL-7B](https://qwenlm.github.io/blog/qwen2-vl/) model on the [ChartQA](https://huggingface.co/datasets/HuggingFaceM4/ChartQA) dataset. This dataset includes images of various chart types paired with question-answer pairs—ideal for enhancing the model's visual question-answering capabilities.\n",
- "\n",
- "**📖 Additional Resources**\n",
- "\n",
- "If you’re interested in more VLM applications, check out:\n",
- "- [Multimodal Retrieval-Augmented Generation (RAG) Recipe](https://huggingface.co/learn/cookbook/multimodal_rag_using_document_retrieval_and_vlms): where I guide you through building a RAG system using Document Retrieval (ColPali) and Vision Language Models (VLMs).\n",
- "- [Phil Schmid's tutorial](https://www.philschmid.de/fine-tune-multimodal-llms-with-trl): an excellent deep dive into fine-tuning multimodal LLMs with TRL.\n",
- "- [Merve Noyan's **smol-vision** repository](https://github.com/merveenoyan/smol-vision/tree/main): a collection of engaging notebooks on cutting-edge vision and multimodal AI topics.\n"
- ]
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ " Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
+ " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
+ " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m844.5/844.5 kB\u001b[0m \u001b[31m15.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m59.6/59.6 MB\u001b[0m \u001b[31m43.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m324.6/324.6 kB\u001b[0m \u001b[31m30.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25h"
+ ]
+ }
+ ],
+ "source": [
+ "!pip install -U -q git+https://github.com/huggingface/trl.git bitsandbytes peft qwen-vl-utils trackio\n",
+ "# Tested with trl==0.22.0.dev0, bitsandbytes==0.47.0, peft==0.17.1, qwen-vl-utils==0.0.11, trackio==0.2.8"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "V0-2Lso6wkIh"
+ },
+ "source": [
+ "Log in to Hugging Face to upload your fine-tuned model! 🗝️\n",
+ "\n",
+ "You’ll need to authenticate with your Hugging Face account to save and share your model directly from this notebook.\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 17,
+ "referenced_widgets": [
+ "3d7dbcc18c1b4dceae74bdfb75a8da8e",
+ "b2ec4b8bf53245c88cb74e59612713fb",
+ "c865a38342ac4b49951d3dad4a774838",
+ "92b7e089d8804be2a4f7a1e7cd82e89d",
+ "b49628cfbdfc40b7956baa4cbf93829b",
+ "8ade50abf0714d2d921fbd74648c5004",
+ "fcb2f724d1ad4157b907d48fa993efd4",
+ "14de7b80d5bf46e7b900682b20d61cef",
+ "10561db48a4b430e98b0e11bd8aa1ef6",
+ "23511e8b562e4f7e99aa2854a9d98c17",
+ "76467e7df06e43cdb2a76c9ecc0f8c15",
+ "582995cfeaf44e118d498cb7ccfd857a",
+ "8a732dcf3d1e4664b99b6f68df75ae17",
+ "23d8b425314a447b8239de0b294e5db9",
+ "30c9d00326c04024a9a171a83352281b",
+ "4cc0e10451564ae190dbe249b15ca94d",
+ "ddaddfb293174a79840350d5c5d98a3e",
+ "a2e17e3dcd684ac89e09de8fa4082e90",
+ "efbd24054785495f9c521b097d487b83",
+ "0bf82ddbeeab48eab8f77dd8d99071c1"
+ ]
},
+ "id": "xcL4-bwGIoaR",
+ "outputId": "289d8507-dde1-46c4-e6ad-eb1d072cc868"
+ },
+ "outputs": [
{
- "cell_type": "markdown",
- "metadata": {
- "id": "QoD6dxPeXDKR"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "3d7dbcc18c1b4dceae74bdfb75a8da8e",
+ "version_major": 2,
+ "version_minor": 0
},
- "source": [
- ""
+ "text/plain": [
+ "VBox(children=(HTML(value=' ],\n",
+ " 'messages': [{'role': 'system',\n",
+ " 'content': [{'type': 'text',\n",
+ " 'text': 'You are a Vision Language Model specialized in interpreting visual data from chart images.\\nYour task is to analyze the provided chart image and respond to queries with concise answers, usually a single word, number, or short phrase.\\nThe charts include a variety of types (e.g., line charts, bar charts) and contain colors, labels, and text.\\nFocus on delivering accurate, succinct answers based on the visual information. Avoid additional explanation unless absolutely necessary.'}]},\n",
+ " {'role': 'user',\n",
+ " 'content': [{'type': 'image',\n",
+ " 'image': },\n",
+ " {'type': 'text',\n",
+ " 'text': 'Is the rightmost value of light brown graph 58?'}]},\n",
+ " {'role': 'assistant', 'content': [{'type': 'text', 'text': 'No'}]}]}"
]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "train_dataset[200]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "YY1Y_KDtoycB"
+ },
+ "source": [
+ "## 3. Load Model and Check Performance! 🤔\n",
+ "\n",
+ "Now that we’ve loaded the dataset, let’s start by loading the model and evaluating its performance using a sample from the dataset. We’ll be using [Qwen/Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct), a Vision Language Model (VLM) capable of understanding both visual data and text.\n",
+ "\n",
+ "If you're exploring alternatives, consider these open-source options:\n",
+ "- Meta AI's [Llama-3.2-11B-Vision](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct)\n",
+ "- Mistral AI's [Pixtral-12B](https://huggingface.co/mistralai/Pixtral-12B-2409)\n",
+ "- Allen AI's [Molmo-7B-D-0924](https://huggingface.co/allenai/Molmo-7B-D-0924)\n",
+ "\n",
+ "Additionally, you can check the Leaderboards, such as the [WildVision Arena](https://huggingface.co/spaces/WildVision/vision-arena) or the [OpenVLM Leaderboard](https://huggingface.co/spaces/opencompass/open_vlm_leaderboard), to find the best-performing VLMs.\n",
+ "\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {
+ "id": "PCJhM6tCw4lq"
+ },
+ "outputs": [],
+ "source": [
+ "import torch\n",
+ "from transformers import Qwen2VLForConditionalGeneration, Qwen2VLProcessor\n",
+ "\n",
+ "model_id = \"Qwen/Qwen2-VL-7B-Instruct\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "2HobU2iPUDWL"
+ },
+ "source": [
+ "Next, we’ll load the model and the tokenizer to prepare for inference."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "awtjIq86JfFF"
+ },
+ "outputs": [],
+ "source": [
+ "model = Qwen2VLForConditionalGeneration.from_pretrained(\n",
+ " model_id,\n",
+ " device_map=\"auto\",\n",
+ " torch_dtype=torch.bfloat16,\n",
+ ")\n",
+ "\n",
+ "processor = Qwen2VLProcessor.from_pretrained(model_id)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "7JtKcuuXUGUT"
+ },
+ "source": [
+ "To evaluate the model's performance, we’ll use a sample from the dataset. First, let’s take a look at the internal structure of this sample.\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "i-eIIdL9lqJJ"
+ },
+ "outputs": [],
+ "source": [
+ "train_dataset[0]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "hLaWWJk_RkVU"
+ },
+ "source": [
+ "We’ll use the sample without the system message to assess the VLM's raw understanding. Here’s the input we will use:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "Ytnr1rePOamM"
+ },
+ "outputs": [],
+ "source": [
+ "train_dataset[0]['messages'][1:2]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "3IK2HOMuRtY_"
+ },
+ "source": [
+ "Now, let’s take a look at the chart corresponding to the sample. Can you answer the query based on the visual information?\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "QavnLzjJUbxf"
+ },
+ "outputs": [],
+ "source": [
+ "train_dataset[0]['images'][0]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "gpLfsCUtUW6I"
+ },
+ "source": [
+ "Let’s create a method that takes the model, processor, and sample as inputs to generate the model's answer. This will allow us to streamline the inference process and easily evaluate the VLM's performance.\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {
+ "id": "_MoRTjFcE8qD"
+ },
+ "outputs": [],
+ "source": [
+ "from qwen_vl_utils import process_vision_info\n",
+ "\n",
+ "def generate_text_from_sample(model, processor, sample, max_new_tokens=1024, device=\"cuda\"):\n",
+ " # Prepare the text input by applying the chat template\n",
+ " text_input = processor.apply_chat_template(\n",
+ " sample['messages'][1:2], # Use the sample without the system message\n",
+ " tokenize=False,\n",
+ " add_generation_prompt=True\n",
+ " )\n",
+ "\n",
+ " # Process the visual input from the sample\n",
+ " image_inputs, _ = process_vision_info(sample['messages'])\n",
+ "\n",
+ " # Prepare the inputs for the model\n",
+ " model_inputs = processor(\n",
+ " text=[text_input],\n",
+ " images=image_inputs,\n",
+ " return_tensors=\"pt\",\n",
+ " ).to(device) # Move inputs to the specified device\n",
+ "\n",
+ " # Generate text with the model\n",
+ " generated_ids = model.generate(**model_inputs, max_new_tokens=max_new_tokens)\n",
+ "\n",
+ " # Trim the generated ids to remove the input ids\n",
+ " trimmed_generated_ids = [\n",
+ " out_ids[len(in_ids):] for in_ids, out_ids in zip(model_inputs.input_ids, generated_ids)\n",
+ " ]\n",
+ "\n",
+ " # Decode the output text\n",
+ " output_text = processor.batch_decode(\n",
+ " trimmed_generated_ids,\n",
+ " skip_special_tokens=True,\n",
+ " clean_up_tokenization_spaces=False\n",
+ " )\n",
+ "\n",
+ " return output_text[0] # Return the first decoded output text"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "5UeNiMJC_uCk"
+ },
+ "outputs": [],
+ "source": [
+ "# Example of how to call the method with sample:\n",
+ "output = generate_text_from_sample(model, processor, train_dataset[0])\n",
+ "output"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "ysh0e9DRUfF-"
+ },
+ "source": [
+ "While the model successfully retrieves the correct visual information, it struggles to answer the question accurately. This indicates that fine-tuning might be the key to enhancing its performance. Let’s proceed with the fine-tuning process!\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "Sw3b76rawti6"
+ },
+ "source": [
+ "**Remove Model and Clean GPU**\n",
+ "\n",
+ "Before we proceed with training the model in the next section, let's clear the current variables and clean the GPU to free up resources.\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "dxkXZuUkvy8j"
+ },
+ "outputs": [],
+ "source": [
+ "import gc\n",
+ "import time\n",
+ "\n",
+ "def clear_memory():\n",
+ " # Delete variables if they exist in the current global scope\n",
+ " if 'inputs' in globals(): del globals()['inputs']\n",
+ " if 'model' in globals(): del globals()['model']\n",
+ " if 'processor' in globals(): del globals()['processor']\n",
+ " if 'trainer' in globals(): del globals()['trainer']\n",
+ " if 'peft_model' in globals(): del globals()['peft_model']\n",
+ " if 'bnb_config' in globals(): del globals()['bnb_config']\n",
+ " time.sleep(2)\n",
+ "\n",
+ " # Garbage collection and clearing CUDA memory\n",
+ " gc.collect()\n",
+ " time.sleep(2)\n",
+ " torch.cuda.empty_cache()\n",
+ " torch.cuda.synchronize()\n",
+ " time.sleep(2)\n",
+ " gc.collect()\n",
+ " time.sleep(2)\n",
+ "\n",
+ " print(f\"GPU allocated memory: {torch.cuda.memory_allocated() / 1024**3:.2f} GB\")\n",
+ " print(f\"GPU reserved memory: {torch.cuda.memory_reserved() / 1024**3:.2f} GB\")\n",
+ "\n",
+ "clear_memory()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "YIZOIVEzQqNg"
+ },
+ "source": [
+ "## 4. Fine-Tune the Model using TRL\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "yIrR9gP2z90z"
+ },
+ "source": [
+ "### 4.1 Load the Quantized Model for Training ⚙️\n",
+ "\n",
+ "Next, we’ll load the quantized model using [bitsandbytes](https://huggingface.co/docs/bitsandbytes/main/en/index). If you want to learn more about quantization, check out [this blog post](https://huggingface.co/blog/merve/quantization) or [this one](https://www.maartengrootendorst.com/blog/quantization/).\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 104,
+ "referenced_widgets": [
+ "b45a7622ec4d4d8986305dcf6d85c0bf",
+ "3ab0220ff74845fbaf546603153f5cb8",
+ "76c3f48584c2454f9ac3e5756d24604f",
+ "f8a009ee72324c3cbe13411430c3f8fb",
+ "2b4f36d611ab419396c9e84c3cb8f399",
+ "e7cbc93b8a284c98bc1e1b1462d9cfb2",
+ "942102ce4e974e41b2361475ca414a93",
+ "2e4557d45259450b9c3a84c186c9bbce",
+ "b8ac9ae1610943d288ed7d8adf144304",
+ "7c9be642c9f9452b94f8cf93e05cdc72",
+ "879673e1f55640849f0ef5310c6b4b11"
+ ]
},
+ "id": "zm_bJRrXsESg",
+ "outputId": "7cc9cfd7-c3da-48af-b83c-b93b50e2ffc0"
+ },
+ "outputs": [
{
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/",
- "height": 17,
- "referenced_widgets": [
- "3d7dbcc18c1b4dceae74bdfb75a8da8e",
- "b2ec4b8bf53245c88cb74e59612713fb",
- "c865a38342ac4b49951d3dad4a774838",
- "92b7e089d8804be2a4f7a1e7cd82e89d",
- "b49628cfbdfc40b7956baa4cbf93829b",
- "8ade50abf0714d2d921fbd74648c5004",
- "fcb2f724d1ad4157b907d48fa993efd4",
- "14de7b80d5bf46e7b900682b20d61cef",
- "10561db48a4b430e98b0e11bd8aa1ef6",
- "23511e8b562e4f7e99aa2854a9d98c17",
- "76467e7df06e43cdb2a76c9ecc0f8c15",
- "582995cfeaf44e118d498cb7ccfd857a",
- "8a732dcf3d1e4664b99b6f68df75ae17",
- "23d8b425314a447b8239de0b294e5db9",
- "30c9d00326c04024a9a171a83352281b",
- "4cc0e10451564ae190dbe249b15ca94d",
- "ddaddfb293174a79840350d5c5d98a3e",
- "a2e17e3dcd684ac89e09de8fa4082e90",
- "efbd24054785495f9c521b097d487b83",
- "0bf82ddbeeab48eab8f77dd8d99071c1"
- ]
- },
- "id": "xcL4-bwGIoaR",
- "outputId": "289d8507-dde1-46c4-e6ad-eb1d072cc868"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "b45a7622ec4d4d8986305dcf6d85c0bf",
+ "version_major": 2,
+ "version_minor": 0
},
- "outputs": [
- {
- "data": {
- "application/vnd.jupyter.widget-view+json": {
- "model_id": "3d7dbcc18c1b4dceae74bdfb75a8da8e",
- "version_major": 2,
- "version_minor": 0
- },
- "text/plain": [
- "VBox(children=(HTML(value=' "
]
+ },
+ "execution_count": 19,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "import trackio\n",
+ "\n",
+ "trackio.init(\n",
+ " project=\"qwen2-7b-instruct-trl-sft-ChartQA\",\n",
+ " name=\"qwen2-7b-instruct-trl-sft-ChartQA\",\n",
+ " config=training_args,\n",
+ " space_id=training_args.output_dir + \"-trackio\"\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "skbpTuJlV8qN"
+ },
+ "source": [
+ "Now, we will define the [SFTTrainer](https://huggingface.co/docs/trl/sft_trainer), which is a wrapper around the [transformers.Trainer](https://huggingface.co/docs/transformers/main_classes/trainer) class and inherits its attributes and methods. This class simplifies the fine-tuning process by properly initializing the [PeftModel](https://huggingface.co/docs/peft/v0.6.0/package_reference/peft_model) when a [PeftConfig](https://huggingface.co/docs/peft/v0.6.0/en/package_reference/config#peft.PeftConfig) object is provided. By using `SFTTrainer`, we can efficiently manage the training workflow and ensure a smooth fine-tuning experience for our Vision Language Model. When doing inference we defined our own `generate_text_from_sample` function which applied the necessary preprocessing before passing the inputs to the model. Here, the SFTTrainer infers automatically that the model is a vision-language model and applies a `DataCollatorForVisionLanguageModeling` which convers the inputs to the appropriate format.\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
},
+ "id": "k_jk-U7ULYtA",
+ "outputId": "3bbe53a4-73a3-40e4-c318-4397670df20d"
+ },
+ "outputs": [
{
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {
- "id": "XG8NuzqjjbgI"
- },
- "outputs": [],
- "source": [
- "def format_data(sample):\n",
- " return {\n",
- " \"images\": [sample[\"image\"]],\n",
- " \"messages\": [\n",
- "\n",
- " {\n",
- " \"role\": \"system\",\n",
- " \"content\": [\n",
- " {\n",
- " \"type\": \"text\",\n",
- " \"text\": system_message\n",
- " }\n",
- " ],\n",
- " },\n",
- " {\n",
- " \"role\": \"user\",\n",
- " \"content\": [\n",
- " {\n",
- " \"type\": \"image\",\n",
- " \"image\": sample[\"image\"],\n",
- " },\n",
- " {\n",
- " \"type\": \"text\",\n",
- " \"text\": sample['query'],\n",
- " }\n",
- " ],\n",
- " },\n",
- " {\n",
- " \"role\": \"assistant\",\n",
- " \"content\": [\n",
- " {\n",
- " \"type\": \"text\",\n",
- " \"text\": sample[\"label\"][0]\n",
- " }\n",
- " ],\n",
- " },\n",
- " ]\n",
- " }"
- ]
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/usr/local/lib/python3.12/dist-packages/peft/mapping_func.py:73: UserWarning: You are trying to modify a model with PEFT for a second time. If you want to reload the model with a different config, make sure to call `.unload()` before.\n",
+ " warnings.warn(\n",
+ "/usr/local/lib/python3.12/dist-packages/peft/tuners/tuners_utils.py:196: UserWarning: Already found a `peft_config` attribute in the model. This will lead to having multiple adapters in the model. Make sure to know what you are doing!\n",
+ " warnings.warn(\n"
+ ]
+ }
+ ],
+ "source": [
+ "from trl import SFTTrainer\n",
+ "\n",
+ "trainer = SFTTrainer(\n",
+ " model=model,\n",
+ " args=training_args,\n",
+ " train_dataset=train_dataset,\n",
+ " eval_dataset=eval_dataset,\n",
+ " peft_config=peft_config,\n",
+ " processing_class=processor,\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "NlDsh4WvWCx0"
+ },
+ "source": [
+ "Time to Train the Model! 🎉"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "p1rgMTBDLboO"
+ },
+ "outputs": [],
+ "source": [
+ "trainer.train()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "w6CykSCtX-Xa"
+ },
+ "source": [
+ "Let's save the results 💾"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 49,
+ "referenced_widgets": [
+ "27d3420d65a545e29cbdae604caa32f3",
+ "37925f7df7324bcb8f7d07389730cf82",
+ "174ecb5e6cd54b2989887e08f7b7ac04",
+ "3b50f08adb95437ead16c8303c971470",
+ "8d9cf624237b4480a2e8b430c7a5e006",
+ "31be17b18a5e48b498bd009692f4a2d6",
+ "dfa21476037b465b9e2143d027433f40",
+ "d0e8e5e0352448ff9266f06b9f97b092",
+ "7dece8a5ac7b4ecf91420f01d60f161b",
+ "e525f59c59f74a2c97ab8a72786127ed",
+ "32f97bb4d25d4d32958d35ac3e897ab9"
+ ]
},
+ "id": "tE8usZw0lgrL",
+ "outputId": "455a0714-04b7-4078-ca3f-ccba0ad01f13"
+ },
+ "outputs": [
{
- "cell_type": "markdown",
- "metadata": {
- "id": "IQ2zuDeGThNe"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "27d3420d65a545e29cbdae604caa32f3",
+ "version_major": 2,
+ "version_minor": 0
},
- "source": [
- "For educational purposes, we’ll load only 10% of each split in the dataset. However, in a real-world use case, you would typically load the entire set of samples.\n"
+ "text/plain": [
+ "adapter_model.safetensors: 0%| | 0.00/10.1M [00:00},\n",
+ " {'type': 'text', 'text': 'Is the value of Favorable 38 in 2015?'}]}]"
]
+ },
+ "execution_count": 12,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "train_dataset[0]['messages'][:2]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 376
},
+ "id": "2hLJrxxTVn6x",
+ "outputId": "0e508f63-e60e-40b8-9e2b-61ebf12750c9"
+ },
+ "outputs": [
{
- "cell_type": "code",
- "execution_count": 6,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "dlp3WnfEuftT",
- "outputId": "f9723cfa-c6bd-4908-b89e-e41e60c2b1e9"
- },
- "outputs": [
- {
- "data": {
- "text/plain": [
- "{'images': [],\n",
- " 'messages': [{'role': 'system',\n",
- " 'content': [{'type': 'text',\n",
- " 'text': 'You are a Vision Language Model specialized in interpreting visual data from chart images.\\nYour task is to analyze the provided chart image and respond to queries with concise answers, usually a single word, number, or short phrase.\\nThe charts include a variety of types (e.g., line charts, bar charts) and contain colors, labels, and text.\\nFocus on delivering accurate, succinct answers based on the visual information. Avoid additional explanation unless absolutely necessary.'}]},\n",
- " {'role': 'user',\n",
- " 'content': [{'type': 'image',\n",
- " 'image': },\n",
- " {'type': 'text',\n",
- " 'text': 'Is the rightmost value of light brown graph 58?'}]},\n",
- " {'role': 'assistant', 'content': [{'type': 'text', 'text': 'No'}]}]}"
- ]
- },
- "execution_count": 6,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "train_dataset[200]"
+ "data": {
+ "image/jpeg": "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",
+ "image/png": "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",
+ "text/plain": [
+ ""
]
+ },
+ "execution_count": 14,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "train_dataset[0]['images'][0]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 35
},
+ "id": "pdb9vErmzdAf",
+ "outputId": "157008ef-e1f7-4968-d55a-eeb41906d807"
+ },
+ "outputs": [
{
- "cell_type": "markdown",
- "metadata": {
- "id": "YY1Y_KDtoycB"
+ "data": {
+ "application/vnd.google.colaboratory.intrinsic+json": {
+ "type": "string"
},
- "source": [
- "## 3. Load Model and Check Performance! 🤔\n",
- "\n",
- "Now that we’ve loaded the dataset, let’s start by loading the model and evaluating its performance using a sample from the dataset. We’ll be using [Qwen/Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct), a Vision Language Model (VLM) capable of understanding both visual data and text.\n",
- "\n",
- "If you're exploring alternatives, consider these open-source options:\n",
- "- Meta AI's [Llama-3.2-11B-Vision](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct)\n",
- "- Mistral AI's [Pixtral-12B](https://huggingface.co/mistralai/Pixtral-12B-2409)\n",
- "- Allen AI's [Molmo-7B-D-0924](https://huggingface.co/allenai/Molmo-7B-D-0924)\n",
- "\n",
- "Additionally, you can check the Leaderboards, such as the [WildVision Arena](https://huggingface.co/spaces/WildVision/vision-arena) or the [OpenVLM Leaderboard](https://huggingface.co/spaces/opencompass/open_vlm_leaderboard), to find the best-performing VLMs.\n",
- "\n",
- "\n"
+ "text/plain": [
+ "'No, the value of Favorable is not 38 in 2015. According to the chart, the value of Favorable in 2015 is 38.'"
]
+ },
+ "execution_count": 15,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "output = generate_text_from_sample(model, processor, train_dataset[0])\n",
+ "output"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "swibyq5AWctZ"
+ },
+ "source": [
+ "Since this sample is drawn from the training set, the model has encountered it during training, which may be seen as a form of cheating. To gain a more comprehensive understanding of the model's performance, we will also evaluate it using an unseen sample.\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "2fEa9ChjZsJw"
+ },
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
},
+ "id": "czZSBgnoef1E",
+ "outputId": "e9532aa4-c4cd-47d6-8c40-c4a36677ceba"
+ },
+ "outputs": [
{
- "cell_type": "code",
- "execution_count": 7,
- "metadata": {
- "id": "PCJhM6tCw4lq"
- },
- "outputs": [],
- "source": [
- "import torch\n",
- "from transformers import Qwen2VLForConditionalGeneration, Qwen2VLProcessor\n",
- "\n",
- "model_id = \"Qwen/Qwen2-VL-7B-Instruct\""
+ "data": {
+ "text/plain": [
+ "[{'role': 'system',\n",
+ " 'content': [{'type': 'text',\n",
+ " 'text': 'You are a Vision Language Model specialized in interpreting visual data from chart images.\\nYour task is to analyze the provided chart image and respond to queries with concise answers, usually a single word, number, or short phrase.\\nThe charts include a variety of types (e.g., line charts, bar charts) and contain colors, labels, and text.\\nFocus on delivering accurate, succinct answers based on the visual information. Avoid additional explanation unless absolutely necessary.'}]},\n",
+ " {'role': 'user',\n",
+ " 'content': [{'type': 'image',\n",
+ " 'image': },\n",
+ " {'type': 'text', 'text': 'What is the value of Slovenia in the graph?'}]}]"
]
+ },
+ "execution_count": 16,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "test_dataset[10]['messages'][:2]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 617
},
+ "id": "ATuQ6ZS6eirO",
+ "outputId": "df17b5b1-4c59-41da-a177-290e845d6675"
+ },
+ "outputs": [
{
- "cell_type": "markdown",
- "metadata": {
- "id": "2HobU2iPUDWL"
- },
- "source": [
- "Next, we’ll load the model and the tokenizer to prepare for inference."
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ ""
]
+ },
+ "execution_count": 18,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "test_dataset[10]['images'][0]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 35
},
+ "id": "9yHJMKHNWcMc",
+ "outputId": "aae2ac9e-40aa-4981-9c74-0fd0268322a5"
+ },
+ "outputs": [
{
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "id": "awtjIq86JfFF"
+ "data": {
+ "application/vnd.google.colaboratory.intrinsic+json": {
+ "type": "string"
},
- "outputs": [],
- "source": [
- "model = Qwen2VLForConditionalGeneration.from_pretrained(\n",
- " model_id,\n",
- " device_map=\"auto\",\n",
- " torch_dtype=torch.bfloat16,\n",
- ")\n",
- "\n",
- "processor = Qwen2VLProcessor.from_pretrained(model_id)"
+ "text/plain": [
+ "'The value of Slovenia in the graph is 1.0.'"
]
+ },
+ "execution_count": 19,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "output = generate_text_from_sample(model, processor, test_dataset[10])\n",
+ "output"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "NUr6jmnAIlh1"
+ },
+ "source": [
+ "The model has successfully learned to respond to the queries as specified in the dataset. We've achieved our goal! 🎉✨"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "Z_Ns3p0Dhjbr"
+ },
+ "source": [
+ "💻 I’ve developed an example application to test the model, which you can find [here](https://huggingface.co/spaces/sergiopaniego/Qwen2-VL-7B-trl-sft-ChartQA). You can easily compare it with another Space featuring the pre-trained model, available [here](https://huggingface.co/spaces/GanymedeNil/Qwen2-VL-7B)."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 822
},
+ "id": "dYJJ6ASKhJ5k",
+ "outputId": "f010e580-a4a1-470b-84c4-95ee999774b8"
+ },
+ "outputs": [
{
- "cell_type": "markdown",
- "metadata": {
- "id": "7JtKcuuXUGUT"
- },
- "source": [
- "To evaluate the model's performance, we’ll use a sample from the dataset. First, let’s take a look at the internal structure of this sample.\n"
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
]
+ },
+ "execution_count": 96,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "from IPython.display import IFrame\n",
+ "\n",
+ "IFrame(src=\"https://sergiopaniego-qwen2-vl-7b-trl-sft-chartqa.hf.space\", width=1000, height=800)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "daUMWw5xxhSc"
+ },
+ "source": [
+ "## 6. Compare Fine-Tuned Model vs. Base Model + Prompting 📊\n",
+ "\n",
+ "We have explored how fine-tuning the VLM can be a valuable option for adapting it to our specific needs. Another approach to consider is directly using prompting or implementing a RAG system, which is covered in another [recipe](https://huggingface.co/learn/cookbook/multimodal_rag_using_document_retrieval_and_vlms).\n",
+ "\n",
+ "Fine-tuning a VLM requires significant amounts of data and computational resources, which can incur costs. In contrast, we can experiment with prompting to see if we can achieve similar results without the overhead of fine-tuning.\n",
+ "\n",
+ "Let's again clean up the GPU memory to ensure optimal performance 🧹"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
},
+ "id": "ei-OZGGx4lHe",
+ "outputId": "81bee1a4-4860-464a-bc6a-ae2fb1695236"
+ },
+ "outputs": [
{
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "id": "i-eIIdL9lqJJ"
- },
- "outputs": [],
- "source": [
- "train_dataset[0]"
- ]
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "GPU allocated memory: 0.02 GB\n",
+ "GPU reserved memory: 0.27 GB\n"
+ ]
+ }
+ ],
+ "source": [
+ "clear_memory()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "9NApMx5S4-sh"
+ },
+ "source": [
+ "🏗️ First, we will load the baseline model following the same pipeline as before.\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 49,
+ "referenced_widgets": [
+ "1102501e7373424a8340e8b874ef616b",
+ "a0c52a65d8d2437b8c1e679cdbde3920",
+ "bd50ecadf2a942659e13e1a560d48922",
+ "42906aaafe7f48b6bb4b50f08ba8eead",
+ "d2a964e5096341199b0b249f1239b8a7",
+ "b71d31e016d34cc7864209d1cddb90f4",
+ "8ae0af9dc38c41cd8087dcd1e3109a7e",
+ "8ad20c4edaf94518b0c3eb2d0d04b89b",
+ "17dc54e6f66446a9941df178234a3421",
+ "127ed2bd36134527beccab1ba25a86b3",
+ "c0f4c16c57f941d3bfab5dcc5816194b"
+ ]
},
+ "id": "VbdSklNAR1q-",
+ "outputId": "a4d7d4e9-d5a2-47d2-88bb-85867f05f8fb"
+ },
+ "outputs": [
{
- "cell_type": "markdown",
- "metadata": {
- "id": "hLaWWJk_RkVU"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "1102501e7373424a8340e8b874ef616b",
+ "version_major": 2,
+ "version_minor": 0
},
- "source": [
- "We’ll use the sample without the system message to assess the VLM's raw understanding. Here’s the input we will use:"
+ "text/plain": [
+ "Loading checkpoint shards: 0%| | 0/5 [00:00},\n",
+ " {'type': 'text', 'text': 'Is the value of Favorable 38 in 2015?'}]}]"
]
+ },
+ "execution_count": 93,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "train_dataset[0][:2]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "fou6XKGM5Uii"
+ },
+ "source": [
+ "Let's see how it performs!"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 36
},
+ "id": "eN3NkkpgR4do",
+ "outputId": "5ed3fb26-580a-4c07-d626-cf8c66619b81"
+ },
+ "outputs": [
{
- "cell_type": "markdown",
- "metadata": {
- "id": "3IK2HOMuRtY_"
+ "data": {
+ "application/vnd.google.colaboratory.intrinsic+json": {
+ "type": "string"
},
- "source": [
- "Now, let’s take a look at the chart corresponding to the sample. Can you answer the query based on the visual information?\n"
+ "text/plain": [
+ "'Yes'"
]
+ },
+ "execution_count": 94,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "text = processor.apply_chat_template(\n",
+ " train_dataset[0][:2], tokenize=False, add_generation_prompt=True\n",
+ ")\n",
+ "\n",
+ "image_inputs, _ = process_vision_info(train_dataset[0])\n",
+ "\n",
+ "inputs = processor(\n",
+ " text=[text],\n",
+ " images=image_inputs,\n",
+ " return_tensors=\"pt\",\n",
+ ")\n",
+ "\n",
+ "inputs = inputs.to(\"cuda\")\n",
+ "\n",
+ "generated_ids = model.generate(**inputs, max_new_tokens=1024)\n",
+ "generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]\n",
+ "\n",
+ "output_text = processor.batch_decode(\n",
+ " generated_ids_trimmed,\n",
+ " skip_special_tokens=True,\n",
+ " clean_up_tokenization_spaces=False\n",
+ ")\n",
+ "\n",
+ "output_text[0]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "o9Id3dzV5Wwy"
+ },
+ "source": [
+ "💡 As we can see, the model generates the correct answer using the pretrained model along with the additional system message, without any training. This approach may serve as a viable alternative to fine-tuning, depending on the specific use case."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "Wgv0-sy8TLPE"
+ },
+ "source": [
+ "## 7. Continuing the Learning Journey 🧑🎓️\n",
+ "\n",
+ "To further enhance your understanding and skills in working with multimodal models, check out the following resources:\n",
+ "\n",
+ "- [Multimodal Retrieval-Augmented Generation (RAG) Recipe](https://huggingface.co/learn/cookbook/multimodal_rag_using_document_retrieval_and_vlms)\n",
+ "- [Phil Schmid's tutorial](https://www.philschmid.de/fine-tune-multimodal-llms-with-trl)\n",
+ "- [Merve Noyan's **smol-vision** repository](https://github.com/merveenoyan/smol-vision/tree/main)\n",
+ "- [Quantize Your Qwen2-VL Model with AutoAWQ](https://github.com/QwenLM/Qwen2-VL?tab=readme-ov-file#quantize-your-own-model-with-autoawq)\n",
+ "- [Preference Optimization for Vision Language Models with TRL](https://huggingface.co/blog/dpo_vlm)\n",
+ "- [Hugging Face Llama Recipes: SFT for VLM](https://github.com/huggingface/huggingface-llama-recipes/blob/main/fine_tune/sft_vlm.py)\n",
+ "- [Hugging Face Llama Recipes: PEFT Fine-Tuning](https://github.com/huggingface/huggingface-llama-recipes/blob/main/fine_tune/peft_finetuning.py)\n",
+ "- [Hugging Face Blog: IDEFICS2](https://huggingface.co/blog/idefics2)\n",
+ "\n",
+ "These resources will help you deepen your knowledge and skills in multimodal learning.\n",
+ "\n"
+ ]
+ }
+ ],
+ "metadata": {
+ "accelerator": "GPU",
+ "colab": {
+ "gpuType": "A100",
+ "machine_shape": "hm",
+ "provenance": []
+ },
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.9.23"
+ },
+ "widgets": {
+ "application/vnd.jupyter.widget-state+json": {
+ "03cfe58d482440f3bf80afc43e53730a": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
},
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "id": "QavnLzjJUbxf"
- },
- "outputs": [],
- "source": [
- "train_dataset[0]['images'][0]"
- ]
+ "0771b04a68e7476787cd2d1e0f2ce30b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
},
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "gpLfsCUtUW6I"
- },
- "source": [
- "Let’s create a method that takes the model, processor, and sample as inputs to generate the model's answer. This will allow us to streamline the inference process and easily evaluate the VLM's performance.\n"
- ]
+ "0bf82ddbeeab48eab8f77dd8d99071c1": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
},
- {
- "cell_type": "code",
- "execution_count": 11,
- "metadata": {
- "id": "_MoRTjFcE8qD"
- },
- "outputs": [],
- "source": [
- "from qwen_vl_utils import process_vision_info\n",
- "\n",
- "def generate_text_from_sample(model, processor, sample, max_new_tokens=1024, device=\"cuda\"):\n",
- " # Prepare the text input by applying the chat template\n",
- " text_input = processor.apply_chat_template(\n",
- " sample['messages'][1:2], # Use the sample without the system message\n",
- " tokenize=False,\n",
- " add_generation_prompt=True\n",
- " )\n",
- "\n",
- " # Process the visual input from the sample\n",
- " image_inputs, _ = process_vision_info(sample['messages'])\n",
- "\n",
- " # Prepare the inputs for the model\n",
- " model_inputs = processor(\n",
- " text=[text_input],\n",
- " images=image_inputs,\n",
- " return_tensors=\"pt\",\n",
- " ).to(device) # Move inputs to the specified device\n",
- "\n",
- " # Generate text with the model\n",
- " generated_ids = model.generate(**model_inputs, max_new_tokens=max_new_tokens)\n",
- "\n",
- " # Trim the generated ids to remove the input ids\n",
- " trimmed_generated_ids = [\n",
- " out_ids[len(in_ids):] for in_ids, out_ids in zip(model_inputs.input_ids, generated_ids)\n",
- " ]\n",
- "\n",
- " # Decode the output text\n",
- " output_text = processor.batch_decode(\n",
- " trimmed_generated_ids,\n",
- " skip_special_tokens=True,\n",
- " clean_up_tokenization_spaces=False\n",
- " )\n",
- "\n",
- " return output_text[0] # Return the first decoded output text"
- ]
+ "0f2fb0be37b14323be7b7ee9e9ef6e3d": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_03cfe58d482440f3bf80afc43e53730a",
+ "placeholder": "",
+ "style": "IPY_MODEL_801d03f0db264fd58221d76b3cbc9a35",
+ "value": "adapter_model.safetensors: 100%"
+ }
},
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "id": "5UeNiMJC_uCk"
- },
- "outputs": [],
- "source": [
- "# Example of how to call the method with sample:\n",
- "output = generate_text_from_sample(model, processor, train_dataset[0])\n",
- "output"
- ]
+ "10561db48a4b430e98b0e11bd8aa1ef6": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
},
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "ysh0e9DRUfF-"
- },
- "source": [
- "While the model successfully retrieves the correct visual information, it struggles to answer the question accurately. This indicates that fine-tuning might be the key to enhancing its performance. Let’s proceed with the fine-tuning process!\n"
- ]
+ "1102501e7373424a8340e8b874ef616b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_a0c52a65d8d2437b8c1e679cdbde3920",
+ "IPY_MODEL_bd50ecadf2a942659e13e1a560d48922",
+ "IPY_MODEL_42906aaafe7f48b6bb4b50f08ba8eead"
+ ],
+ "layout": "IPY_MODEL_d2a964e5096341199b0b249f1239b8a7"
+ }
},
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "Sw3b76rawti6"
- },
- "source": [
- "**Remove Model and Clean GPU**\n",
- "\n",
- "Before we proceed with training the model in the next section, let's clear the current variables and clean the GPU to free up resources.\n",
- "\n"
- ]
+ "127ed2bd36134527beccab1ba25a86b3": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
},
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "id": "dxkXZuUkvy8j"
- },
- "outputs": [],
- "source": [
- "import gc\n",
- "import time\n",
- "\n",
- "def clear_memory():\n",
- " # Delete variables if they exist in the current global scope\n",
- " if 'inputs' in globals(): del globals()['inputs']\n",
- " if 'model' in globals(): del globals()['model']\n",
- " if 'processor' in globals(): del globals()['processor']\n",
- " if 'trainer' in globals(): del globals()['trainer']\n",
- " if 'peft_model' in globals(): del globals()['peft_model']\n",
- " if 'bnb_config' in globals(): del globals()['bnb_config']\n",
- " time.sleep(2)\n",
- "\n",
- " # Garbage collection and clearing CUDA memory\n",
- " gc.collect()\n",
- " time.sleep(2)\n",
- " torch.cuda.empty_cache()\n",
- " torch.cuda.synchronize()\n",
- " time.sleep(2)\n",
- " gc.collect()\n",
- " time.sleep(2)\n",
- "\n",
- " print(f\"GPU allocated memory: {torch.cuda.memory_allocated() / 1024**3:.2f} GB\")\n",
- " print(f\"GPU reserved memory: {torch.cuda.memory_reserved() / 1024**3:.2f} GB\")\n",
- "\n",
- "clear_memory()"
- ]
+ "14de7b80d5bf46e7b900682b20d61cef": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
},
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "YIZOIVEzQqNg"
- },
- "source": [
- "## 4. Fine-Tune the Model using TRL\n"
- ]
+ "174ecb5e6cd54b2989887e08f7b7ac04": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_d0e8e5e0352448ff9266f06b9f97b092",
+ "max": 10107280,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_7dece8a5ac7b4ecf91420f01d60f161b",
+ "value": 10107280
+ }
},
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "yIrR9gP2z90z"
- },
- "source": [
- "### 4.1 Load the Quantized Model for Training ⚙️\n",
- "\n",
- "Next, we’ll load the quantized model using [bitsandbytes](https://huggingface.co/docs/bitsandbytes/main/en/index). If you want to learn more about quantization, check out [this blog post](https://huggingface.co/blog/merve/quantization) or [this one](https://www.maartengrootendorst.com/blog/quantization/).\n"
- ]
+ "17dc54e6f66446a9941df178234a3421": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
},
- {
- "cell_type": "code",
- "execution_count": 9,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/",
- "height": 104,
- "referenced_widgets": [
- "b45a7622ec4d4d8986305dcf6d85c0bf",
- "3ab0220ff74845fbaf546603153f5cb8",
- "76c3f48584c2454f9ac3e5756d24604f",
- "f8a009ee72324c3cbe13411430c3f8fb",
- "2b4f36d611ab419396c9e84c3cb8f399",
- "e7cbc93b8a284c98bc1e1b1462d9cfb2",
- "942102ce4e974e41b2361475ca414a93",
- "2e4557d45259450b9c3a84c186c9bbce",
- "b8ac9ae1610943d288ed7d8adf144304",
- "7c9be642c9f9452b94f8cf93e05cdc72",
- "879673e1f55640849f0ef5310c6b4b11"
- ]
- },
- "id": "zm_bJRrXsESg",
- "outputId": "7cc9cfd7-c3da-48af-b83c-b93b50e2ffc0"
- },
- "outputs": [
- {
- "data": {
- "application/vnd.jupyter.widget-view+json": {
- "model_id": "b45a7622ec4d4d8986305dcf6d85c0bf",
- "version_major": 2,
- "version_minor": 0
- },
- "text/plain": [
- "Loading checkpoint shards: 0%| | 0/5 [00:00"
- ]
- },
- "execution_count": 19,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "import trackio\n",
- "\n",
- "trackio.init(\n",
- " project=\"qwen2-7b-instruct-trl-sft-ChartQA\",\n",
- " name=\"qwen2-7b-instruct-trl-sft-ChartQA\",\n",
- " config=training_args,\n",
- " space_id=training_args.output_dir + \"-trackio\"\n",
- ")"
- ]
+ "319ce7779dd54087a79748cff15dd380": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_5d1335feb15d470eb70727f1fc85fc64",
+ "placeholder": "",
+ "style": "IPY_MODEL_5b0be6b9dfc046769a90b0167faa9023",
+ "value": "adapter_config.json: 100%"
+ }
},
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "skbpTuJlV8qN"
- },
- "source": [
- "Now, we will define the [SFTTrainer](https://huggingface.co/docs/trl/sft_trainer), which is a wrapper around the [transformers.Trainer](https://huggingface.co/docs/transformers/main_classes/trainer) class and inherits its attributes and methods. This class simplifies the fine-tuning process by properly initializing the [PeftModel](https://huggingface.co/docs/peft/v0.6.0/package_reference/peft_model) when a [PeftConfig](https://huggingface.co/docs/peft/v0.6.0/en/package_reference/config#peft.PeftConfig) object is provided. By using `SFTTrainer`, we can efficiently manage the training workflow and ensure a smooth fine-tuning experience for our Vision Language Model.\n",
- "\n"
- ]
+ "31be17b18a5e48b498bd009692f4a2d6": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
},
- {
- "cell_type": "code",
- "execution_count": 20,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "k_jk-U7ULYtA",
- "outputId": "3bbe53a4-73a3-40e4-c318-4397670df20d"
- },
- "outputs": [
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "/usr/local/lib/python3.12/dist-packages/peft/mapping_func.py:73: UserWarning: You are trying to modify a model with PEFT for a second time. If you want to reload the model with a different config, make sure to call `.unload()` before.\n",
- " warnings.warn(\n",
- "/usr/local/lib/python3.12/dist-packages/peft/tuners/tuners_utils.py:196: UserWarning: Already found a `peft_config` attribute in the model. This will lead to having multiple adapters in the model. Make sure to know what you are doing!\n",
- " warnings.warn(\n"
- ]
- }
- ],
- "source": [
- "from trl import SFTTrainer\n",
- "\n",
- "trainer = SFTTrainer(\n",
- " model=model,\n",
- " args=training_args,\n",
- " train_dataset=train_dataset,\n",
- " eval_dataset=eval_dataset,\n",
- " peft_config=peft_config,\n",
- " processing_class=processor,\n",
- ")"
- ]
+ "32f97bb4d25d4d32958d35ac3e897ab9": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
},
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "NlDsh4WvWCx0"
- },
- "source": [
- "Time to Train the Model! 🎉"
- ]
+ "341897caa36f49c082e98ea94d559ddb": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
},
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "id": "p1rgMTBDLboO"
- },
- "outputs": [],
- "source": [
- "trainer.train()"
- ]
+ "375ede44354d4b4da527d5291c8e863a": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_a62f4664a5ac40d785893e4eff1e34c0",
+ "placeholder": "",
+ "style": "IPY_MODEL_1aa67fff82344f299f5c73a419871b03",
+ "value": " 10.1M/10.1M [00:00<00:00, 10.4MB/s]"
+ }
},
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "w6CykSCtX-Xa"
- },
- "source": [
- "Let's save the results 💾"
- ]
+ "37925f7df7324bcb8f7d07389730cf82": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_31be17b18a5e48b498bd009692f4a2d6",
+ "placeholder": "",
+ "style": "IPY_MODEL_dfa21476037b465b9e2143d027433f40",
+ "value": "adapter_model.safetensors: 100%"
+ }
},
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/",
- "height": 49,
- "referenced_widgets": [
- "27d3420d65a545e29cbdae604caa32f3",
- "37925f7df7324bcb8f7d07389730cf82",
- "174ecb5e6cd54b2989887e08f7b7ac04",
- "3b50f08adb95437ead16c8303c971470",
- "8d9cf624237b4480a2e8b430c7a5e006",
- "31be17b18a5e48b498bd009692f4a2d6",
- "dfa21476037b465b9e2143d027433f40",
- "d0e8e5e0352448ff9266f06b9f97b092",
- "7dece8a5ac7b4ecf91420f01d60f161b",
- "e525f59c59f74a2c97ab8a72786127ed",
- "32f97bb4d25d4d32958d35ac3e897ab9"
- ]
- },
- "id": "tE8usZw0lgrL",
- "outputId": "455a0714-04b7-4078-ca3f-ccba0ad01f13"
- },
- "outputs": [
- {
- "data": {
- "application/vnd.jupyter.widget-view+json": {
- "model_id": "27d3420d65a545e29cbdae604caa32f3",
- "version_major": 2,
- "version_minor": 0
- },
- "text/plain": [
- "adapter_model.safetensors: 0%| | 0.00/10.1M [00:00},\n",
- " {'type': 'text', 'text': 'Is the value of Favorable 38 in 2015?'}]}]"
- ]
- },
- "execution_count": 12,
- "metadata": {},
- "output_type": "execute_result"
- }
+ "6d358c3999024558bbdf63cc8ff3b0c8": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_63e7a6485906469aa9b709f3b119f9be",
+ "IPY_MODEL_1aac4bfb05c14e42a3f4372fc535ece6",
+ "IPY_MODEL_fc3de4763c3f462785f4cde31c35c68e"
],
- "source": [
- "train_dataset[0]['messages'][:2]"
- ]
+ "layout": "IPY_MODEL_7411cc7b1f224a10984238aec1967a44"
+ }
},
- {
- "cell_type": "code",
- "execution_count": 14,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/",
- "height": 376
- },
- "id": "2hLJrxxTVn6x",
- "outputId": "0e508f63-e60e-40b8-9e2b-61ebf12750c9"
- },
- "outputs": [
- {
- "data": {
- "image/jpeg": "/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAgGBgcGBQgHBwcJCQgKDBQNDAsLDBkSEw8UHRofHh0aHBwgJC4nICIsIxwcKDcpLDAxNDQ0Hyc5PTgyPC4zNDL/2wBDAQkJCQwLDBgNDRgyIRwhMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjL/wAARCAFnAaYDASIAAhEBAxEB/8QAHwAAAQUBAQEBAQEAAAAAAAAAAAECAwQFBgcICQoL/8QAtRAAAgEDAwIEAwUFBAQAAAF9AQIDAAQRBRIhMUEGE1FhByJxFDKBkaEII0KxwRVS0fAkM2JyggkKFhcYGRolJicoKSo0NTY3ODk6Q0RFRkdISUpTVFVWV1hZWmNkZWZnaGlqc3R1dnd4eXqDhIWGh4iJipKTlJWWl5iZmqKjpKWmp6ipqrKztLW2t7i5usLDxMXGx8jJytLT1NXW19jZ2uHi4+Tl5ufo6erx8vP09fb3+Pn6/8QAHwEAAwEBAQEBAQEBAQAAAAAAAAECAwQFBgcICQoL/8QAtREAAgECBAQDBAcFBAQAAQJ3AAECAxEEBSExBhJBUQdhcRMiMoEIFEKRobHBCSMzUvAVYnLRChYkNOEl8RcYGRomJygpKjU2Nzg5OkNERUZHSElKU1RVVldYWVpjZGVmZ2hpanN0dXZ3eHl6goOEhYaHiImKkpOUlZaXmJmaoqOkpaanqKmqsrO0tba3uLm6wsPExcbHyMnK0tPU1dbX2Nna4uPk5ebn6Onq8vP09fb3+Pn6/9oADAMBAAIRAxEAPwD2Ofwnp1zcSzvc6yHkcuwj1q8RQSc8KsoCj2AAHao/+EN0v/n61z/we3v/AMeroKKAOf8A+EN0v/n61z/we3v/AMeo/wCEN0v/AJ+tc/8AB7e//Hq6CigDn/8AhDdL/wCfrXP/AAe3v/x6j/hDdL/5+tc/8Ht7/wDHq6CigDn/APhDdL/5+tc/8Ht7/wDHqP8AhDdL/wCfrXP/AAe3v/x6ugooA5//AIQ3S/8An61z/wAHt7/8eo/4Q3S/+frXP/B7e/8Ax6ugooA5/wD4Q3S/+frXP/B7e/8Ax6j/AIQ3S/8An61z/wAHt7/8eroKKAOf/wCEN0v/AJ+tc/8AB7e//HqP+EN0v/n61z/we3v/AMeroKKAOf8A+EN0v/n61z/we3v/AMeo/wCEN0v/AJ+tc/8AB7e//Hq6CigDn/8AhDdL/wCfrXP/AAe3v/x6j/hDdL/5+tc/8Ht7/wDHq6CigDn/APhDdL/5+tc/8Ht7/wDHqP8AhDdL/wCfrXP/AAe3v/x6ugooA5//AIQ3S/8An61z/wAHt7/8eo/4Q3S/+frXP/B7e/8Ax6ugooA5/wD4Q3S/+frXP/B7e/8Ax6j/AIQ3S/8An61z/wAHt7/8eroKKAOf/wCEN0v/AJ+tc/8AB7e//HqP+EN0v/n61z/we3v/AMeroKKAOf8A+EN0v/n61z/we3v/AMeo/wCEN0v/AJ+tc/8AB7e//Hq6CigDn/8AhDdL/wCfrXP/AAe3v/x6j/hDdL/5+tc/8Ht7/wDHq6CigDn/APhDdL/5+tc/8Ht7/wDHqP8AhDdL/wCfrXP/AAe3v/x6ugooA5//AIQ3S/8An61z/wAHt7/8eo/4Q3S/+frXP/B7e/8Ax6ugooA5/wD4Q3S/+frXP/B7e/8Ax6j/AIQ3S/8An61z/wAHt7/8eroKKAOf/wCEN0v/AJ+tc/8AB7e//HqP+EN0v/n61z/we3v/AMeroKKAOf8A+EN0v/n61z/we3v/AMeo/wCEN0v/AJ+tc/8AB7e//Hq6CigDn/8AhDdL/wCfrXP/AAe3v/x6j/hDdL/5+tc/8Ht7/wDHq6CigDn/APhDdL/5+tc/8Ht7/wDHqP8AhDdL/wCfrXP/AAe3v/x6ugooA5//AIQ3S/8An61z/wAHt7/8eo/4Q3S/+frXP/B7e/8Ax6ugooA5/wD4Q3S/+frXP/B7e/8Ax6j/AIQ3S/8An61z/wAHt7/8eroKKAOf/wCEN0v/AJ+tc/8AB7e//HqP+EN0v/n61z/we3v/AMeroKKAOf8A+EN0v/n61z/we3v/AMeo/wCEN0v/AJ+tc/8AB7e//Hq6CigDL03QLPSrhp7ebUndkKEXWpXFwuMg8LI7AHjrjPX1NFalFAHgvx2uYda1qPRG1O3tV0vTpNQKyyqnmzEgJGMnlioOAPWuhl+JGuSaN4E/sODTri61+OSKU3hcKkqKq5yp4AYtkYOQMDHWumt/hzpM3iHXNY12Cx1ibU5UMa3Fkp+zRqu1UUsW5xjLDGcdKwtE+EMujz+H8+ITPb6JezXUERs8ErJt+QtvPQqTnHfpRDSyfk/zv+f4Dlvdef5f5r8Tn5Pi340t9AutXm0jQ/I0rUjYaiVkl3TNuA/dLn5QBxli2SQcdRWn4q+LOp2HiTVdP0caDDBo8KyXH9rXLRy3bEbikABGWxkc55x+OjdfCP7T4W13RP7c2/2rqp1HzvsmfKywOzbv+bp1yPpVzWPhxqEuv32reHPFVzoUmpRLHfpHarKJdowGUkgxtjPI5ycgijWy/rovwvcHa/8AXf8AyMa5+KOv6h4i8P2HhvR7a5j1fTY73ZNnfCTIRJltyghVVu3Jx9Kpad40tvClh8Q9YTSLdZbXWWiVIXkzcSMxAZyzMB6naAPau2t/AYtfGul+IV1W4mFhppsPLuQZZJeWPmNKWzn5umKz/wDhVdlcad4qsL+/eeHXr03gMcQRrZs7hgkndg98DPpQ+tvP/wBKWn3Aul/L8nf8SzoerfECP7SNf8Pabcg2nn20ml3HlgydoXErZDH+8PlHv25zQPiZ4hm8b6XoesDw3PHqSy/JpN0ZZbN1G7bKdxXPBGB16g8YO1a/DrVptP1G117xrqWp/arE2MQjiFvFChH3jGpId+2484yPcVNF+FN5pmpeG7y68TtenQxJHDEbFY0MTLtCgK3BHJLHcTx6UP4vL/h/+B/W868vn/w3/B/rbn9M+LXiufTtD1m80zSP7KvdU/s2fyjIJixJwyAkhQB6kkkHgDmtKy+JfiG78VvbNF4dhsE1M2DabPeeTqW3O0SASMqsCSCABk9B61ct/hF5HhLStC/tzd9g1Yal532THmYJOzbv469cn6VLqHwv1LVbxbe/8Z3114fW8F2unXFuskoIOQouGJbAPTjpx701uv6/l/4I59bf1v8A8A7DxZqsuh+EdX1S3AM1pZyyx5GRuCkjP414bDY+E9K8PeHPEGo+KrvR/GF8BqB1Nop7lpgScoyKdu3kDtkDnINfQl3awX1nPaXMYkt542ikQ9GVhgj8jXlk/wAGL640N/Dz+Nb0+H42aS0sjaRlonySu6TOXUEk7flB7YxSjpK/p/wf09bWY3Zq3r/X9d9Bk+s3dj8QfH9xo+m2H9p2WmQXCzyLM5uMIrbWXzMdMgbQD0znvoWnxQlu7GDU0gtnsLbQv7T1EIGLiYkqsSHOF+ZX6g8Cuj0zwaNP8c614ka9Ey6nbxQG1MONgRQud245zjpgday/Cvwr0vw3oOvaPJcG7tdXkff+78sxxEYVAcnJXJ+b9KWqjbrb8df80/kG7u/L8l/k18znvCnxZ1PUvEOjWerjQZLbWg32dNMuWkns2AyqzqSeSMDjHf0xVr4sXdzf+I/CXhD7TJb6drFywvTE5RpUUqPLyOx3HjucVseGvAGsaHfWH2zxnqF/penIyWenpELdQOiiVlbMoAHAYfkOK1fGngq28YWloftc1hqVhL59lewjLQvx2/iHAyOOg5qnbTTS/wCBKvr3t+Jyt/8ADy38HaN4qu9Dv5bfRbjR7hX0ht8iCXyz+9Ds5IOBjGPx6Yw/h54v8QaRD4J0S/stOGjatayJavE7tcKUBO5/4cE9gOh68V1lp8NLh21i+1zxFNq2tajYSael49qsSW8LLjCxKcZzyTkZ9uSXWnwz+yv4Nb+193/CNpIv/Htj7RvGP7/yY/Gp16+X/t3+aG9tPP8AT/I4rw/43uvDXwm03UtH0fT4WudcNo1qDKUKsWyQXkJDHA5JIHpXT6b498VtdeK9JvNF0651nR1jkhSzuPLhZHGfneUj7o5J4zyMCli+Efl+CdP8Of25n7Hqo1L7R9k+/jPybd/HXrn8Kk8QfCZNfvvE9y+tyQDXFtwES3z5JixjPzfODjp8v1pv+vuX63Kdrt/1u/0sQ+B/iFrGs+NJ/DmryeH7wiyF3Fd6HO0kS4YAoxJOTz2xjHfPGb8cdHOv3fhfS0/1k73Yj5x84iyv6gV0vh74e3ej+LbfxFe+IW1G5TTvsMitZrEGG7KlQpwoAAG3B7nPNbWveF/7b8Q+H9V+2eT/AGRPJN5XlbvO3LtxnI24+hpTSlZLv+v+RMG1d+X6f5nzn4t12Xxx4J0wiYmPw/pMb3WOM3DyrCAR/uru/GvXbvxj4hXUNJ8K+E7LTpdQTSI764m1Ev5YTaAFUJg7icc9Ofxpx+DdmnhrxNpFtqflNrd4tx5/2bPkIr7lj27hux83OR16cVoa38N7i8v7DVdE8Qy6Pq1vYiwluVtVmWaIDHKMRg575/xpttp+bv8Ag/ybS9EFkmvLT8V+auc3J8XtV1LRvD8+l22j6bNqJmW5utZldbWF4uqBlxy3UZPtz1rI8Za94q10eAruOLQo2m1BfK2XBnja7Riu7fGzDySCOAdwOQeldvF8M7vRtH0uz8K+K7/R5bJXWWRoluI7necszxMQu7PRuw454NVJPhCsfhrSrCw1+W21PT79tQXUDaq4aZvvHysgAcDAycY703vfzX5/5C6W8n+RiW93rVh8SvH15Zx2cms2+kWsvllGaF5FjQsoGQ2Dggc+ldZ4P8eXHi/U9OjtY7ZbU6Sl5fkIxZJ2YqI1OcAfK55BOMU+18MzeFtc1zxfd3dzrE91YwxS2trZDzZGjRVLKA2CWIztwMZxVX4ReFx4f0PUbxrCexbU76SeK3uV2yxQA4jV17HGTj3ojsk+i/z/AM7/ACCXdeX5L/K3zML446Vfa1e+FbHTHK37TXMluQcEukYcAHsSVwDWT4a+IdvqPim88VXMTedY+FyLyBeCJo5jlfbPBHoGr1jWvDX9r+ItA1b7X5X9kyyyeV5e7zd6bcZyNuOvQ1zsHwo0qHxV4h1Xzz9i1u1e3nsVjxsZyCzq+e5GcY4JqVdXt5/fay+//Ip2dvl+d2c/4X+Lmp3+vaRa6uuhS22sq5t49KuGkuLRgMqs6knkjA4xzn6VTvviX4q1LwrZ6xp9xp2nQ6lrA0yKFbRprq3GfvZZwrNx90oOo5rqdH8Ba7oIhMnjDUtTsdNt5F0/TIkW1ycYRZHB/eYAAG4YB56ZB840/RPFOm20GraVNfP4i87ctle+Fd0u5nwyyX7xjPyk5fcMjpjtSs5W/rf/AC08ha2/rt/wx0/ir4l+LfCdzO9zD4cFtaSxxGzuLsf2hdpkAzKkbFUDckAglfQ4qPTbnxPc/tAXzAaRsXT08wHzM/Yy4Zcf9NeRnPy9auXHwYu7uw1uyPiuWK01a4F41v8AY1fZNuDEs+4M4HIAyo5zzXST+A7xfHVv4n07xA1m/wBmjtby3NosguI0IyAxPyZwOmT71OtlffX8V/n+H3Clqml/Wq/T8dzhPCnjS68O/D7Q9TstM0200ufW3tL6JBM3lozf6xWaRiDwc5yORjFb+u/FG/0nSL6/it7Bln1dtM0ppSyR4Th5ZXzgqGB6beB171o2fwsgg+GN74Mn1Lz1uZHlW7+z7fLYsGU7Nxzggdxn2qxd/DK0uPAmkeHYtQltrrSSk1pqEUYDJOuTv2Z6EknGfxpv/L9L/dZ/eU99PP8AW333X3Efw/8AHl14l1PVdF1NtKmv9PCP9q0iYy2s6MP4ScnI4B56+mK4n4swabcfFvw/Hq+jX+sWR0999lYIzTPy+CArKeDgnnoK9Q8LeHNU0aa8u9a8TXmt3tyVG6RPJhiUDACQqSqk9yOv55i1Dwd9v+IeleLPt+z+z7Z4Psvk58zdu537uPvdMHpQ1dx8v8mJPSX9dUecfDS61LT9D8Wa14X0qR9BeYf2Vpt1eopjcZEjOzP8gAwSCckAcnrVm0+I/ivUrnWtC8zwreX0elm9t7vTp5JLdQCA6OckltpOMYwQM5B42bj4QLLpHibSYtdeGw1m7W8iiS2/49nDbsfe+dTwMYXoOau6T8NLi08QjV9S8QyajK+lNpsym0WHcpPBTacIAMDGD3OeaTvKNn2/T/MatGV13/VfoeZ6ddahafBrww2qWGk3tg2sQpYIWnDoC0u5n2uvzA9MEjHUGu38SfEHxXZ+JfFWmaNY6RJDolpHeebd+YDs2BnGFb5mOePugY5NPh+EV+vhiz8P3Hisz2VjfxXlop09VMSoXJTIfLbi/UnjHTmty8+Hn2vXfFep/wBqbP7fsFs/L+z58jCBd2d3zdM4wPrTm7ttef5K34igkrJ+X/pWv4GTb/EbVdc1bQNL0uCysJdR0n+0pbi+jeVBwf3aKrJnBBJOenauU0n4oeMJtL026kvNFjfWLicpc6tE1vZWixceWrocsW6gsc8Y5607W/BepW2q6do015fx6dpmmRwQXb6D/atvO2fmKwBHEL+pJJIxjA67nhzw5451bSY5m8TXehzWM8ltZP8A2cqR3NoOFZ7M4WNgfu5AIHboaNG215/m/wDgfdfuLVJJ+X5f1+R33hDWbrXvDFpqF7Fax3Lhlk+yXCTwsykqWR1ZhtOM4zkdD0rcrnvBfhSHwb4eXTI7p7qRpXnnnZAnmSN94hRwo9BXQ03uCCiiikMKKKKACiiigAooooAKKwkj+0+MblvPuBFa2sYMSzuIy7luSoO3IUDt39RTI7a5g8MSrp9zMb26VngN3cM7ZbJCgsTjC8D6Z9aOlw62OgorB8OiNpr10OoxOhSKW0vZ2mMTgbsqxZgQQy9D2p+oajqEF7ew2v2ZxFYmeNXRsiTJChjuwQcH0PFAI26K5D+157Ka5fyYTe3d61uk0NvLICkaZyYwxJwcrwQO5xU0mu6taLL9shtVlj077Q8So2UmLbVUkMQQTngdMdTR/X4XD+vxsdTRWBqmrajZJcmOOIxxyIpmWB5hECm5i6KQTzjp0DA84qe51K7SDTIITbG9vsDzMFokwm5mAyCw4wBkdRQBsUVx1pNd+JtRto7v7G9pBG7XFu9uXSRhIyBuW77GIyDj34I0UX+2tT1JJ7m4htLFxAkUE7Q5bYGLsyEE/eAAzjg8egB0FFcTAs+na8s1m9vchRa2Es82WlnY/M53Z67SpySfu4x3q0bzUYHurq2Sxa6m1FbTLRuonRcD+8dpX5+QCDt6Uf1+X+aD+v6+5nWUVyh8Q6k1ptU2aTxx3FxLO0TeX5UblQQm7OW/3uMHr0rodNmuLjS7Se6VFuJIVeRYwQoYjJAzQBaooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKAM+50Wxu7prmRJhK6hX8q4kjWQDOAyqwDdSOQeOKZfeH9M1G5FzcwOZhsxJHM8ZG3JXBVhjG41p0UAUE0WwjWACFiYJvPR3kZm8zBG5mJyxwcck9vQU+bSrOe/S+kiJnQBch2CsASRuUHDYJyMg4PIq5RQBlt4e01o9nlTKBM1wrJcyKyO2dxVg2Vzk5AwOelFz4d0u7YNNbscRCHCzOoKjO0EAgHBOQTyDyOa1KKAMyXQNOmihjeKX9yWKuLiQOd33ssG3NnvknNTXml2l9DFHLEQITmIxSNEU4xwyEEDBxirtFAGXpGmvZGaaWKCGSUIiwwHckUaDCqCQCe56Drj3Mk+iafc3rXckLea4VZNsrqsoHQOoIV+v8QNaFFAFGXR7GYhmiYMLj7TuSV1PmY25yCD04x0xSQ6NYwOrJE/yztcKGldgsjAgkAnA+83HTmr9FAGM/hTR5Ldbd7eUxKrIF+0y/dbGV+9yvAOOg7VqwQJbW6QR79iDau9y5x7kkk/jUlFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFYGr+KrfSLueA2F7ci1txc3csHlBbeIlsO291LD5H+4GPy9Omd+uP8ReG9Q1LVZriK0029WSJUt5r24kR9OcZBkhCo3zchsho2yoG7gEAGjN4rt4b9oRYXslok6W0t+gj8mKR9u1SC4fq6AkKQC3J4OL51vTxc3Vu07K9sheQtE4XA67WI2sRxkKSQSAcZrAfw/rQ+0aYHspdMurqO5lunlZZ1wUZ1EYQq25kODvGN/Q7eZdb0GeW9nu9PhnR1USkpKCZX3DiNHYxowxu5ADOIyxIU0hnUowdFYZwwyMgg/kelLVTS/tf9mW/27d9p2/Pv27vbdt+XdjGdvGc44xVuqe5K2CiiikMKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigChJq0Ef23KSf6Jt8zAHOfTmrIu7cyiLz4vMJxs3jdnGcY+lZF5pF7LdXf2eWAW95s80yA71x/dxx+dPl0aZ7qWVWi+a5ilBJOdqjBHTrXEquIvrH+rv9LHS4Umt/wCtP1uXItXsZfNPnxokb7N7uoDH25qwLy2IJFxCQE3k7x931+nvWYNMvI7fy451Gbl5XVZGTcp6DcBkVDBoM0cVkryR5iLLNjJDoW3AdPUfqaI1cRonH/h9P8/wYOnS/m/r+vzNj7ZakyAXMOYxl/3g+Ue/pSHULIMqm7gDN0HmDJ/WsZtBuTC8QkiAWOVI2ycvvbPzccY/GpL/AEW6niMEEsaweWqpHvZVQg5JwB82fel7fEct+T+tf8rf8APZ0r25jRj1O2e9ltC4SWNguHIG8kZ+XnmiHU7WWLzGkWJTI0Y81guSDjjms+XR7l7qZg0IjmmjkLbjuUJ6DHf61F/YNwMsWikJ8xShldFwzZB+Xk+47+tL2uJT+Hv+at/X+Q/Z0X17fkdDRTY08uJE4+UAcU6u85QooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACis231Np7ySHFqAhbKrcbpcA4zs29/r3qS2vp5LlIbi2EPmxmSPEm5gBj7wwNp5HTPfmoU4sC9RRRVgFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFMllSGJ5ZDhEUsxxnAFRRXsM0byDzI0QZZpomjAHr8wFK62AsUVHBPHcwpNE26NxlTjGakp7gFFFFABRRRQAUUUE4GaACis+21Fp45H2QtsTd5cM2989gRgYNT29xLJM8M0SJIihvkfeMHPfA54NZxrQlaz3LdOSvcs0UUVoQU729No8a/uAGBJaaby1GMcZweeaZNfvFcJDi2BZVOZLjbknPC/Kc9KnngleVZYZY0cKV/eRb+D6cgj88VXOmssXkxTIImiET7ogWKgY4II9T1Brmn7a75dvkbR9nZX/U0KKQDAAHalrpMQqFby2ecwLcQtKMgxhwW49qmrKha4ScJE07Eu5eOWLbGoOTkNjnnHQnr09Mqk3FrzLhFSTNMSIZDGHUuACVzyB9KdWZZRXceoOZ4YxuiG+RZCdzZP+yPy7DFadOnNzV2rBOPK7BRRRWhAUUUUAFFFFABRRRQAUUUUAZ6adKJYy08RiikaWNVgCtuOfvEHB+8egGf5rY2V3bSvJcXUM5cfM4hKufTncQAOeAB1+tVbzVL1tSew0y2ilkiQPM8z4Vc9Bx3q1pOo/wBpWjSPEYZopGiljJztcdRmsYuHNZfqBfooorYAooooAKKKKACiiigAooooAKpapvNnsjJDvIigCXyyfmGRuzkcenNXaZLFHNG0cqLJGwwysMg/UUpK6sBjRtvkisZDNCBMyy7bp33HZuADnDdDnHHT066GmsxtnVnZxHK6K7HJIDEDJ746Z9qkNjaG2FsbWD7OOfK8sbfXp0qaONIo1jjRURRhVUYAHsKiMGndgOooorQChPfOt7DDCqlDKI5WPYlScD34Gfr+VW31d3vY45JID5kjRm3RT5kJGcFjnvj0HXgnvbm0fT550ne0g81X8wuI1yx56nHPX9KelhtuVme5nlVGLJG5UqhPpxk9SOSetZNTuBbooorUCC9jaaymiRdzOhUAMFz+JB/lVG2jniE7ta3TQ4XbBNMsjlweSCWIA6fxdug76tUbvWNOsJlhuruOKQ/wk8/j6VElFPmbsAaV5yWSxT20kDJx87Kd3J6bSf1q9SKyuoZWDKwyCDkEUtVFWVgCiiimAUUUUAFIw3KRnGRjNLRQBRSxnXB+0Rh44zHCUh2hc45Izz0HTAqSzt5rdWEsscm45LLGVJPqSWOarXWoXbXz2dhBHJJGoaR5Gwq56D61nS+Lo4QY5LOT7QhKum4BQR7/AP1q4ZV8NSd5O1vW3/BOpUq1RWSv9x0lFcl/b2t3v/HnY7VPRghb9TxR/ZfiK+/4+bvylPUGTH6LxU/2gpfwoSl8rL7x/VHH45JHS3V9bWUbPPMibRnBIyfoO9Z6a8qtGbu0mtYZf9XLJgg/XHSs+PwbHtJmvHZyOCqgAH8c5q3JpN/qCxQalPAbaI5/cg7nIGBnPT8Kl1cXJ35OXstH976fIahh19q/4fcaSapp7/dvbcn08wVOlxDJ9yWNv91gaw38H6e33ZbhT/vA/wBKgfwZAfuXkg+qA1ftcYt6afoyfZ4d7Ta+R09VrvULSx2/aZ0jLdAep/Cud/4RG4j/ANTqOP8AgBX+Rp1pZ3WjXjy3lvLfiRNqyRKZGX2welS8VXWkqfL53ul9w1QpPad/Lb8zpopY54lkidXRhkMpyDT6zNDtpbeyk82PyvNmaRIv+eanoK067aUnOClJWbOecVGTSCiiitCAooooAKpajePa27+SqtPsZ1DdAFGST7f41dqreabZ36sLm2ikYqVDsgLKD6Ejiple3ugVb+9u7aNJkMQj2bsNEzbj1ILAhYx7nP6VqA5GaoPpUZj8mKeaG3KbGhj2hGH4g4z/ALOKrav4isNFTY7eZOB8sKHn8fSo5uS8puyA12ZUQu7BVAySTgAVyereM0ST7LpMf2mcnaJMErn2H8R/zzWaItd8YSBpD9m0/PHUL+A6sf0+ldXpOgWOjp+4j3SkfNM/LH/AfSseepW+DRd/8hmFpOha+ZpdQn1M2lxOMMDGJCR7joPb+lUp4Nb8J3cl1HKbq0kbdIxHDE9Sw7H3/wD1V31IyhlKsAQRgg96p4WNvdbT73EZeja/ZazF+5bZOBloWPzD6eorVrkNZ8H/AL37bozeROp3eUDgZ/2T2Pt0+lN0jxe8Uv2HW0MMynb5pXHP+0O31pRrOD5aunn0YHXSypDE0jnCj07+31qoNUV4YHhtp5XmTzBGm0Mq+pywHcd6fc2ovlhdLqWMId6tFtIbjg/MCDVFbHUrfT7e0ikjlULiYvKY2P8AsqVQ4HXnGffvW0pSvpsBqwTJcQRzRklHUMpIxxUlRwKUt40MaR7VA2IcqvsDgcfhUlWtgCoJbqOKeKEhi8hwMDpweT+VT1nzadI9ys0d3KP3okZSFwOCOPlz+vrUVHJL3VcuCi37zJkvkeZU8qUIzFElIG1mGeBznseSMcVaqjHFeNe+bcRwMik+WVlPyD127eT75+nfN6im5NO4TSWwVFc3MFnbvPcSrHEgyWY1S1fW7TRrfzLh8yMPkiX7zf4D3rkoLTVPGV0Li7YwWCn5QOn0Udz7/wD6qipW5XyRV5f1uQCXNle6TdapcanImphmaJRNtKEfdVV7g8VOnjXUoowJ9KLEAAt8y5P5V1NrommWaRiGyg3R/dkZAXz67jzmr9ZxoVEvisxnFD4gbW2yaWVI64m/ptqVfiBanG+xmHrhwa68gMMEAg9jUTWlu5y1vE31QGq9nX/n/ARzcfjSO9dLbT7GZ7uRtqLIQF9ySDRd+LbjSJTbanp4+0YDKYZPkZT355HIrVvtBtrlI2tQlncxNvjmhjGQfcdx7UWOi+TdSXl9cm+u3UIJHjChVHOAo6UuWve1/npb7hnOnxvf3JxZaTu9OWf+QFH9p+Mbv/VWPkZ/6ZBf/QzXb4wMCin7Cb+Kb+WgHEf2V4wu/wDW3/k5/wCm23/0AVJZW9xoYvIL/S59Rkn5WeFPMDjGNrE8iuzooWGSd03fz1Ecd4V8RQQ20ek3uYJoiVRpOAeTwfQjpXY1h674atdZQyDEN2B8soH3vZh3rAsNd1Dw3cjT9Yjd4Bwj9So9Qf4h/L9KmM5UbQqbdH/mM7uiore4hu4Ent5FkicZVlPBrM1bWI7WXyEu4YZEKNJvZckFhwAfbJJ7D68dMpqK5mI2KKyJLm4YS3kd0fKjnVBCFUq65APOM5OSRg46Vr0RlcArH1nXodLQxpiS5I4Tsvuf8Kqax4iKObLTv3lwx2l1Gdp9B6mnaN4dEDi8v/3tyTuCk5Cn1Pqa4auJnVk6OG36vov82dcKMYR9pW+S7lfStN1eeSTUJL02ssw7xhiw9wentW3Y6VbWUf3BLMSWeZ1BZie+avUVtRwlOkl1fd6mdTETn5LyCiiiuowCiiigAooooAKKKKACiiigAooooAKKKKACqeq339m6XcXmzeYlyF9T0H6mrlRzwR3MEkEyB45FKsp7ilK7TtuByWrzeJLeztv9NgLXkixBYkClGboA3p71Y0fwZb2zC41JhdXB52nlAff+9+NaNp4ctLW5imM91ceT/qUnl3LH/ujFbFc8KCcuaf53GAAAAAwB0FFFFdIgooooAKzNX0Ky1mLbOm2UD5ZV+8v+I9q06KmUVJWkB5+kus+DZwko+06ex4/u/gf4T7fzroIvFAdIriXTrmGxkYKty+MDPGSOw962ruKGe0minA8l0IfPpiuHlOozaLHYzSeXpO4It0YCWKg/LkZ6ZArhqSeGdlLTp/XbzNIU5T+FHfUV5cLjUdPl22eryPEOhBbH/fLcVr23iXWlhO7ZPgcuYen5cVCzWhez38tTWOErPW1vU7qqN9qQtJY4I4HuLiQErGnHA7k9hXB3Pim/mYq166jpiMbcflzVjT7147uKfT7l76+fKmHym+71OWJFQ8xdTSnFrz0v8l1LWHhD45p+X/BO2sNQW+WQeW8U0TbZIn6qe34Vj6/4rh00ta2YE94eOOVQ+/qfauZlu9SvNckjSK4W+kOJEQbNuOPXpjHJq1baZf6Fefav7MWVh0YguF9xg8H3qHj6vLyuLX9636LZg8PGetOS9C5pHha41C4/tLXWd3c7hCx5P+96D2//AFV2aqqIERQqqMAAYAFc5beMLZjtubeSJu5U7h/Q1sW2rWF5gQ3UbMf4ScH8jzXZhq2GatTkm/xMalCrD4olyimGaJZBG0qCQ9FLDJ/Cn12JpmNgooopgFFFFABRRRQAUUUUAFVb/TrXU7YwXUQdD0PdT6g9qtUUmk1ZgcBNaar4NujcWrG4sGPzA9P+BDsff/8AVXVabq1h4gtMIfmGC8LHDKQcj6jI61oTyQRxN9oeNYyMHzCACPxrgdRsrGDV4JtDvTHK0gBRM4Un0bpj2rgqTWF2fu9uvyNIUp1PhR3EtjaCZruQFSCHYmVghI6ErnaSMDkjsPSud1HWrnVrj+z9KVtjcNIOCw/oKq+I21G0SCLUL/zYJDklEAxjGcgYz1rU0XVfD1tbiK2u0Rz99phsZj7k8VjOpPEVHRXuR67XfkjoiqdCKm/eb27epd0fQoNLQOcSXJHzSY6ewrWpkcscyB4nV1PRlORT69KlShSgoQVkc05ynLmk9QooorQgKKKKACiiigAooooAKKKjlnhgUNNKkYJwC7AfzoAkopAQwBBBB5BFLQAUUUUAFFFFABSEhQSSABySaWqeq28t3pdxBCcSOmBz19vx6VM5OMW0rsqKTkkxbfVLG7mMMFzG8g/hB6/T1q3XJ301xJb2hs9HuIZrVg5ZosAY7DHUGrNl4tgc+XexNA44LLyv5dR+tcNPHwUuWq7dnZpfidMsLJrmgr/mdHRUcFxDcxiSCVJEPdTmpK7001dHK01owooopiCmySJDG0kjqiKMlmOAKo6nrFrpcf71t0pHyxL1P+ArnUg1PxPMJJm8izB444/Adz71x18YoS9nTXNPt/n2Oilh3Jc83aPf/Im1HX59SdrDSomcOCrPjlh3x6D3P6Vbj0nVZrCLT7ua2W0G3cUyZCBzt9PxrRt7O30i3WO1tpJGY4OwAs3uScAfmKkGoqyp5UE0jkElFC5XBwcknHXjgmsI4dtuWIleT6La3bzNZVbJKlHRdXv6jYNG062x5dnFkdCw3H8zV0AAYAAA7CkjkSaJZI23IwyD6inV6EIQivcSS8jklKUn7zK1zp9neD/SbWGX3dAT+dZEvh02N4l7oYhgmAKvHMWKOD+o/CugqnLqAhuBG1vP5e9Y/OwAm44wOTk8kcgEfkaU4QerRJX0nTZ7Wa6vL2WOS8umUyeWMKoUYAGea1KpRalHLMq+VKkcjFY5mACuRngc57HqB0q7TgopWiBXubC0ux/pFvHIfUrz+fWse58I2MuTBJJAfTO4frz+tdBTXdIkLyMqIoyWY4ArKrhqNX+JFP8Arua061SHws4yOGwttOns7mBzqgJCYQlmP8JU+nSrKzeKrZRuiMoA7hWP6c1032y28jz/ALRD5OceZvG38+lSJIkqB43V0YZDKcg1yRwK2jUtp9nTTz3v6nRLEv7Ub+uv3djlv+Ek1a3/AOPnTMY77GX+eakj8Zwn/W2ci/7rhv8ACunqOS3hm/1sMb/7yg1f1bEx+Gr96RHtqL+Kn9zMZPFVlNhYIbiSZjhY9oyT+dTp4gto3aK+R7OZcHZIM5HqCKLvRY98VxpyQ291E25TtwreoOKjGiG+uWudY8qV9oRI4SyqoHv1PWpvjU7aN+nu28+tyv8AZ2r9Px/yJ/8AhIdK/wCfxf8Avlv8KP8AhIdK/wCfxf8Avlv8KZ/wjWkf8+n/AJEf/Gj/AIRrSP8An0/8iP8A41f+3f3PxJ/2X+9+A/8A4SHSv+fxf++W/wAKibX0lZ/sNpNdxxjLyJwB9M9TTv8AhGtI/wCfT/yI/wDjUSaVfae8qaVJbpbynO2bcTGcYyPX8aUnjF8drf3dX+I0sO/hvfz2/ApTeMFZtlnZu7HoXP8AQZ/nUXmeJtS+6ptoz7bMfn81dFp2nxadZxwRgEqPmfGCx9at0o4WvUSdao/RaA69OD/dwXq9TlovCMkz+ZfXzOx67OT+Z/wrRXwxpawtH5LFiMeYXO4e47fpWxWZqOpx28nkrcxRSKUZ9zDOCRwAfbJPoKp4TC0I8zj9+v5i9vXquyY1PD1kXZrkzXhK7R9pfftHtxVO58FaPcZKRywE943/AKHNX3nmYSXSXB8uOUIIgFKsuQOuM5OeOfStKtoU6Mk4qJjU5m7yZxMngW6t3Mmn6mVbtuBQ/mP8KZs8ZaZ0ZrmMe6yZ/P5q7mij6rBfA2vRmdzjtOvtV1+9ktru5fTWgQMY4UKO5J6ndzgf1p1l4yt7QSWmovJNLDIyC4jQFZFBwD1rodQ0bT9UZGvLZZGQYDbipx6ZBFMOg6SYljOnW21Rgfuxn8+tT7KrH4X9/X5DKsPi3RJv+XwIfR0Yf0xWhDqmn3H+pvrZz6LKCfyzWbN4P0SXpamM+qSMP64qhN4BsG/1N1cIf9rDD+QqubELdJiOrLKE3lgFxnOeMVStdZ029nMFteRSSj+EHr9PX8K5KfwNewQyfZNREnB/dlSm726kVPeWcmvQWWnw6TNYGEjzZ5YtqooGCF/vZNJ1qvWNv1GdNc61plpkT30Ckfw7wT+Q5rHufHOlQ5EKzznsVTaP15/So7bwHp0WDPPPMfQEKP8AH9a2Lbw/pNpgxWEOR0LjefzOaf8AtEuy/EDmT401O9Yrp2lZPTo0h/TFRwT/APEwa48W27APFi3LxkoOeRgd67tVCqFUAAdAKiW7tnuWt0uImnXlog4LD6jrSdCTs5Tv+X3AZXhdJE0p8pIkDTu1sknVYj93+tbdQw3lrcSPHBcwyun31RwxX6gdKmremlGKSEFFFFWAUUUUAFRTXEFsoaeaOJScAuwXP51LVO9dVK5E6MQcSww+Ycd16Ejt+XWoqS5Y3KgruxLLeWsDqstzDGzDIDuASKivdLsr8f6RArN/fHDD8ao4uIETaJ4ZvIRUjjh3IzDPBbnA5xyR9a2RnAz171lFqsnGa0/r+tkXJOm04s5Wfwxd2chm0u7YEfwsdrfn0P44pIvEmoafIIdUtGP+0Btb/A11lMlhjnjMcsayIeqsMiud4HkfNh5OPluvuNliubSrHm/My18S6fIimIzSOeTGkZLD61n6h4oMpFtpSNJK/G8ryPYD1q0NPn0i/ln02zSeGZQDH5gUoR6E9qtaRpptFlnnjjF1O7O5UfdBP3QfSs/9rq/u2+Xu0nt5Pz/Ar9xD30r9tfzXkZmmeGSZPtWqMZZWOfLJyM/7R710oAVQqgADgAdqWiu2hh6dCNoL/NnPVrTqu8iC7SSSLYkUEynh45jgEfXB/lVJrCfyosJE7ru48502AnIUEDlR0wR27VqUVU6UZu7JjUcVZEVrALa1igByI1C5xipaKK0SSVkS3d3YVm3Nnc3F2r+VartcFbkMRKqgglcY78j72OenatKilKPNoxGRFpcg1BJWihSKOVpFKTO2Sc4wh+VOuTg8/jWvRRRGKjsAVDdFVgJeN3AI+4m4qezAe30NTUU2rqw07MxdsmPMIuAnnlhP5J837mM7Mfh93GO3etDTwy2vKsMuxBcYLAnOSOxP4fQdKtUVlTo8kr3/AK/r5+ZcqnMrBRRRWxmVpLwRTBGgm2bgnm4AXJ6Dk5PUcgYoS8Ek2xIZTHuK+aACuR1HXPY84xUM9tPNcq3l242sCs4YiRVzkrjHfkde/So4dNaK6VhHCAkhcThiZCDn5cY6c+vbp6czlV5tFpf+v6/E2UYW13/r+v0NOiiiukxGyOI42chiFGcKMk/QVWGoIFk8yGWJ02/u22ljuOFxgkcnjrVmTzPLbytu/Hy7umfesw6bJJHL+7ghBKssMbnYSDkknAxnocD8+lY1ZTT9w0gote8aEExmUloZImBwVkAz+YJB/A1LVSxtmtlkzHFEHbIiiOVXjHHA6/QVbq6bbiuYmSSegUySNJU2OMrkHGfQ5FPoq2r6MkrtZQNP5xVt+QxAdgpI6ErnBPTnHYVYoopKKWyG23uFBzjjrRSMoZSrAFSMEHvTEZcDXgvmtprmcb42Ku6RjJBHMeAcDno+T096m03z2M8kl1LPCX2xeYqA8cE/Ko6n+XvUtvp9tayb41ctt2gvKz7R6DcTgdOnoKnhiSCJYo12oowBnNZxi09QH0UUVoBDcXdtaKGubiKFScAyOFBP402a/s7d1Se7gidhlVeQKSPbJqDUXRCuRcxuVIE1vB5hx3XhWIB47Dp1rNxdW0cewXME/wBmjVIooN6MwBwrMd2Bk45K/U9RlKbTsB0NFIudo3DBxzS1qAVivmS9iFvBPlHcmCSHZGh2sCwYAAkk+rfePHcbVFTKPMBiaWjLc24AuWEcJRhLCY1h6fKpIG4cerdOvrt0UUQjyqwBRRRVAFFFFABRRRQAUUUUAFFFFAFcX1u0xi3ncCRkqQpI6gNjBPXjPY+lLBeQ3LERMxOMjchXcPUZHI9xVRUlmudk1jIkCFvLAZNvORuOGz36Y4z37NsracXUckqzqsUZQCZ0brjgbeo46nmuZVaja069n/X+Zs4Qs9fxRqUUUV0mIUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQBzniXUL+0vLGGymnQShywgt1mY4xjCn/ABpJtfm0u0iFwBdSiISSbgY5QCf4kVSq4yBywrdks4JbqG6ePM0IIjbJ4z146VBd6RY3zs9xBvZ1CNh2XcByMgEZxXO6dRNuL3HoZ0/icW5uFe0PmQMS6iT+DAIbp3JAx70P4jmVxANP33XnLEY0m4+ZdwIYgVqNplk8k0jW6l5ohFIST8yDtTYtIsYTGUhO6OTzFZnZjuxjJJOTxxzT5at99P8Ag/5fiIz18Q7tSSz8mNlkZ0WWJ2YBlGcHKAH8CcVnQeIr7+wwZgBcSW0ssU4IOSpxyuMD9a310XT0uFnW3xIrM6/O2FLdcDOBmmJoOmojILc7WjMWDIxAU9QMnjPtUOFZr4v6t/mPS5Ustfe5uo7dbSWRQVjkmVW4Yrkk4XaBn3z7Vu1SXSLFbhJ1gw6kEfO23IGAducE474zV2uiClb3hBRRRVAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUVRk1rSodVj0uXU7JNRkGUtGnUSsOTkJnJ6Ht2q9QAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFAHCXyS+ZqejmwvXv7rVYrqC4W1kaEqGiIkMoGxSioRgkH5MAHIz3dVr/ULbS7KS7vJPLhTAJCliSTgAKASzEkAAAkkgCs7/AISzSPsP2vzbkjzvI8gWU32jzMbtvk7PMzt+b7v3eenNAF+ePUGlJt7q1jj7LJbM5/MOP5VH5Or/APP9Zf8AgG//AMdqnL4t0aKytrvzriWO5DtGkFnNLJhDhy0aIXXaeDuAweDg8Us3irSYZoYle7uTNCk6NZ2M9wvlvnaxaNGABwcZI6UAW/J1f/n+sv8AwDf/AOO0eTq//P8AWX/gG/8A8dq/RQBQ8nV/+f6y/wDAN/8A47R5Or/8/wBZf+Ab/wDx2r9FAFDydX/5/rL/AMA3/wDjtHk6v/z/AFl/4Bv/APHav1Wv9QttLspLu8k8uFMAkKWJJOAAoBLMSQAACSSAKAIfJ1f/AJ/rL/wDf/47R5Or/wDP9Zf+Ab//AB2qn/CWaR9h+1+bcked5HkCym+0eZjdt8nZ5mdvzfd+7z05pJfFujRWVtd+dcSx3Ido0gs5pZMIcOWjRC67TwdwGDwcHigC55Or/wDP9Zf+Ab//AB2jydX/AOf6y/8AAN//AI7VHUPGGjabAlxcSXjWzwrOtzb6fcTw7G6HzI0Kj863AcgEd6AKPk6v/wA/1l/4Bv8A/HaPJ1f/AJ/rL/wDf/47V+igCh5Or/8AP9Zf+Ab/APx2jydX/wCf6y/8A3/+O1fooAoeTq//AD/WX/gG/wD8do8nV/8An+sv/AN//jtWrm4hs7aW5uZUigiQvJI5wqqBkkn0xWTF4t0eW0uLjzriMW+zfFNZzRS/OcJtiZA7bjwNoOSCBkigC55Or/8AP9Zf+Ab/APx2jydX/wCf6y/8A3/+O1UHizSDp/2wS3JXzjb+SLKYz+YBu2+Ts8zO35vu/d56c02TxfosdrbXAuJ5RcKzRxwWk0soVTtYtGil0Cng7gMHg4PFAF3ydX/5/rL/AMA3/wDjtHk6v/z/AFl/4Bv/APHauRSxzwpNDIskUihkdDkMDyCD3FPoAoeTq/8Az/WX/gG//wAdo8nV/wDn+sv/AADf/wCO1fooAoeTq/8Az/WX/gG//wAdo8nV/wDn+sv/AADf/wCO1foJwMnpQBQ8nV/+f6y/8A3/APjtHk6v/wA/1l/4Bv8A/Hap23i7RLsTNHeOiRQtP5k1vJEkkS/eeNnUCRRkfMhI5HqMzWPiPS9QiupI55IRaKHnF5byWzRqQSGKyqpC8H5sY4PPBoAm8nV/+f6y/wDAN/8A47R5Or/8/wBZf+Ab/wDx2mf2/pQ0H+22vY003Z5nnuCo25wOCM5J4AxknpV+GVJ4Y5o23RyKGU4xkEZFAFPydX/5/rL/AMA3/wDjtHk6v/z/AFl/4Bv/APHav0UAUPJ1f/n+sv8AwDf/AOO0eTq//P8AWX/gG/8A8dq/RQBQ8nV/+f6y/wDAN/8A47R5Or/8/wBZf+Ab/wDx2r9ZEPibSZ9TOnx3Ennb2jV2t5Fid1zuRZSuxmGGyoYkbW44OACx5Or/APP9Zf8AgG//AMdo8nV/+f6y/wDAN/8A47UGmeJdK1e5a3s5pjJ5fmr5ttLEssecb42dQJF5HzKSOR6ihfE2jyaVJqcV6stnHKYfMiRn3vnbtQAEuSSANoOc8ZoAn8nV/wDn+sv/AADf/wCO0eTq/wDz/WX/AIBv/wDHadpmq2mr27zWjS4RzG6TQvDIjYBwyOAynBB5AyCD0NXaAKHk6v8A8/1l/wCAb/8Ax2jydX/5/rL/AMA3/wDjtX6KAKHk6v8A8/1l/wCAb/8Ax2jydX/5/rL/AMA3/wDjtX6KAKHk6v8A8/1l/wCAb/8Ax2nRxamJFMt3aNHn5lW1ZSR7HzDj8qrT+JtJttU/s6WeQTh1jZhbyNFG7Y2o8oXYjHK4VmBO5eORkg8S6Vc6r/ZsU0v2gu8as1tKsUjpncqSldjsMNkKxI2t6HABrUVmDxBpTR6lIl4jppuRdmMFvLIGSOByQOoGTnjrxUmmavbaskjW0V6gjIB+1WM1sTn0EqLn8M0AX6KKKACiiigDM1+S6g0p5rHSP7Vu43Vobbei/Nn72XIA29eueK5m1s9Uge11k6JqM1+l1I95DNJbLJNvjCb4gJmRVXaqhWcHbnljy3c0UAcRY2esaPqA1j+xbi7N4LjzbOCaESW2+Xemd7qhyPvbWPzYxkc1nv4b1iztYYYbLUmv/sMUUFzYaksNvbzLuOZE3IzIrP0IlBUfdHIPo9FADYwwjUOQXwNxHQmnUUUAFFFFABWZr8l1BpTzWOkf2rdxurQ229F+bP3suQBt69c8Vp0UAcNa2eqQPa6ydE1Ga/S6ke8hmktlkm3xhN8QEzIqrtVQrODtzyx5Z1jZ6xo+oDWP7FuLs3guPNs4JoRJbb5d6Z3uqHI+9tY/NjGRzXb0UActZ6HexWHhzTrhFa3tP393sYbPMQZRBnkgOdw4/wCWY6V1NFFABRRRQAUUUUAU9V3f2VdFNPGoOIyVtCVAmbsuW+UZPc1x6WetXySard6HfJq0U9vMYppbdUkjRm/cxbZWwQGZsuRuYjkDAXvKKAOI+x6uusf8JINFuSxujnTfOh88R+SI9+d/l7tw6b/unrniqs2j6vb+XqMGnatHeXL3Lypp11aq8aPIGWKQSkp05LISytuwSDmvQaKAMvw5pj6N4a03TZGBktbZImIJIyBzgnk/jWpRRQAUUUUAFMlAaFw0fmAqQU4+b254596fRQB599g1rXba7+3eHrrT7pLRorGJ5bf7LCoZW8vMcjMWcooLbQAowAOS2vF9vutQvNZu/Dl2irbRQR2Ej27TTMsjOWGJDGApK4ywOQ3A4z1VFAHDWqaovgVrCfwrqDXsSPFFG0lqTudXG9T52AAGweQfm4B5rp9AluZNGtlu9PuLGaJFjMU7RsxwAMgxuwx+OfatKigAooooAKKKKACuINrqWrao1peeHb3T9PhaZLJoXtvJVmVl899su8khjhQnyliTuOCvb0UAcbYW2p3Umn/2hoEsEemWEsEkbSQut2zKi7IgHPyEKf8AWbOq8dcJpU+s29jqcb+FdSQTXUkwQ3dvGzRucYRklOHA55Kjjhs4rs6KAOe8J2N1ZW9+09pPaQz3PmQQXUqy3CrsVSZJFZt5JU4Jdjt2jPGB0NFFABRRRQAUUUUAcfqC6lda+bJ/DV4NGS5jmM1q9sBdSAqQ8mZVYIpAJUKWbaOcZVmWOn6qH0zSZtLlig069e4OoGWIxzIPM27QG3723rnKgfe5PGezooA4RbfVLg6/aJ4Xv7O2voVjgJntUVQse0j5Xk2k9vkI6ZxWt4YtL+3vLySS21OzsHRBHbanei5l80Ft7hhJJtUgoMbuqn5R1PS0UAFFFFABRWLPdXVpqDy3c08VsJMR4iR4nXHAyPnVs9zhe3NPXWZV2ie0WN38pkVZd2UdtuTwMEdxyPehag9DXorKGsO1yIlthtBmLuZPurGwUnGOSc9P1qKXWruC3ieTTv3kxBiVHaQbcZO7YhII9lI5HNHS4eRtUVWgnmubYSrD5W+MMiy5DBjnhlwMY4rIh1K7s123RuJbp9gFvOiLyWCkq6fKVyw4OSOKOtgOgorJj1aeW4jt/sirL+880iXhNhA4O35s7hjgVDHrkoSD/RWkjMMEkkplG4eYcDgAZOfoOv0oA3KKyLPV5b3VJLZEhVIlcsN5ZwQ20BxgbM8kDnI9MVXM2oRzCAX5l3lI5ZRGmIJCeicc8Z4bOPlz15AN+isKW61CC3mjW4Dm3ukjaaRRvdWKHGAAv8ZGcdumTkSTS6hBqpmleRbAzLGqh48HcAB8uwtjcefmB9qANmisWa6kE8k7388MSXAiWOO3EiEDGd5CkjOTzkAcfiker3K27EQC4dDNJIWcJiNZGAAwDk4HTjpyaANuisSPV50u5zJGr2f2hY1k3hWXMasPlxyMnqT3qOPXZbuI7YWt5Flg6q3zRu+P4lHPB6ZHoTQBv0Viarq4stVtYhdwxqGXzYWK7pA52jGeeDzxUD6zqaxyNLbWyRrHcMWinJceW20YymPz69eOhFqB0VFZUWp3P9oPbzW8QjNx5MbJISceXvyQR9Pz9smrLrdzNaxy21sEU+SZHMgJXew4AI5GOp468UAb9FYia/LIbgx6bcOiKxjIjk+fBxz8mOeo2luB68VMdXk/sv7XHBFNJ5mxkhkZ1T13EJuGO425FAGrRWSutAxuwjhk2rCd0M29Dvcrw2OcY/8A1ULrRC+bPbiK3MssYfzMn5N3JGOM7T3oA1qKxf7cna6eBNOlYqCuQHxvC5xu2bcZ4zuzntWhZ3qXymSJf3W1SHz1JGcY9gR+ftQBaorFinuwba7e8d0nuDGbfYgVVJYDBxuyMAnJPf8AB8UuoTf2hE9zFFJHKoDhRiJCqk4yOSATye/bHFAGvRXOrqOowzIE/wBLh8uaRWlIjMiKUw2QvXlgOACMH3rfilWaFJUztdQwz6GgB9FFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAU20qza5M5jfcW3lfNbYW9SmduffHvTE0axjt5IFibZIFB3SuSAvKhSTlQDyMYx2rGvPHFpZaldW0umaibe0uorSe9UReUkkgTbx5nmEfvF5CHrUb+O4Y7G/1BtD1b+zbGWSOW8HkFMxvschfN34BBP3egNC1BnQ2+mWlrt8mHG0MoyxbhiC2cnnJA61EuiWCReWscigEFWE7hlwMAK2cqMEjAIHJrLn8b6XBfarZtHdGbTRCXAjGJjIQqiMk/MdxAPTkik1rxlDot/eWp0nUbwWVoL25ltvJ2RREtyd8ikn5G4UGjpcFrsb6WsSIU+d1KBCJJGcEDPXJPryep71Ql0CzeHy08wAsmTJI8mFVg20bm+UHHb29Ko23jCC9v7qG10vUJrW1Kie+HkiJA0ayA4MgkPysOiGqsfj+1fRBq39i6utvIIGtsxxf6SsrhEKMJNoOSMq7KwBzijr/XyA6ODTrW32eVFtKKygliThiC2STySQDk80g0yzWPYIfl2xpjceiHKjr2NY2qeMrfQ9KgvtV0zULQzSmP7OwieRVALNI2yRlCBQSTuz7Z4pNa8ZQaNfXdt/ZWo3gs7MXtzNbeTsiiO7k75FJ+4xwoNAWuXrLR5rW7eRr1nhO7ES716n03lR/wABVami0OwhgMCLP5RGNhuZCF5yCAW4ORnI5rNPjXSzK5ijuprSFkSe9jjBihdwpRGyQ2SHXJCkLn5itT6f4qsdSbRRDFcL/a9q91b71UbUUISGweD846Z70WDcuSaNZS26wMs/lqxbi5kBZsg5YhsseB1zinR6RZRTrMschdSG+aZ2BbGNxBOC2O5596xLzx9pVla3V69vevYQGVFu441Mc0sYYvGnzZyNjDLAKSMBiaW68b2+mWlndavpOpadDd3K28bT+S4G5S29vLkbagxyT09Mc0LyB6bm3NpNnPO00iSbnIZlWZ1ViMYJUHBPA5I7Ckl0exmVVeFsKX+7Iy5DHLA4PIJ7HisS/wDG0dncxQxaHql4JrtrKOSA24Vpl3Er88qnohOcY988UkfjiJ9O1HUm0PVUsLAT+bcsbfaxhJDqqiUtnKkDIA96E9LodnexvNpdm9w07Qku2SQXbaTjGSucZxxnGcU2LR7GHO2NySUJLyu5+Q5XkknAPaqOkeJo9V1KXTpdNvtPvEt0uhFdeUd8TEqGBjdx1UjBIPtW5RsTuQSWkEsc8bplZ/8AWDJ54A/DgDpVeTRrGXdvjkIYsSBO4HzfeGM9D1x0zz1q/RQMpT6VZ3Du8kb7nIYlZXXkDAIweDjjI6jg0w6Jp5MWICoiCqqrIwXCnK5AODg9M5xWhRQBSGlWqtIU89BJncqXEiqMnJIAbCnPcY70o0y2W2MC+eqs29mW4kDsfUvu3H8+1XKKAM9tF09jETAcx4x+8bnB3Atz8xzk5OeSfWpn020ktvs7whovM83aSfvbt2fzq1RQBTfT4vPe5gLR3Dc58x/LLYxlkDAN2/KlsbCOygjRCcqGztJCksck7c469OuBxVuigDN/siNNUjvIn2qCzNExZl3H+JRu2qeTk4Ocn1preH9PdZFcXLCUguGvJjuIxgn5vYflWpRQBQbRrJ0CuJ3xnl7mRmwcZGS2SpwOOlXEjWMtt3fMckFiQOMcA9Bx0FPooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooA5208G6VD4i1DW7q0s7u9ublJ4ZpbVTJb7Y1QBXOT1XORjrWXpvgBbG51XzX0mW31I3InkXS9l2yTMWKGfzDkDI/h7DpXbUUraW8rDuzhbL4bpav4dll1aWebSmka5dov8Aj9LMHG75jt2uqsOvTFWvEfw+0/xLqGoXt2YDPPZR21tJJarI1q6M7CRSeuSwyvGQuM812FFVcS0ONi8E3EPiq81yO70rzrqRXMz6SHuocRLGRFMZMLnBPKEcnINZVx8LXuorkSX+lxPMkastrpAihnKSrJuuIxJiVjtxkbcBm4549HopdvIDi1+HtveRxwavLbG0ggkggtNIhl06JBIcyEqkp3bhgEE468c1UuPhda6hZump3cF5drpsNjbXUlkpeBomcrKNxPJ3KCOM7T64Hf0Uf1/X3h/X9fcc0fC1xHc3ZtdXkt7W/mW5vI0j+cyBVH7t93yK2wblIYkE4K1T8P8Aw807w7eaNd2a2sdxYWcltcSw2ixvdltnzuQc5Gw9c/ePPr2NFC0A4298CzXGjXuiW+tS2+lTidkiEWZFeXfkM+4b4wXJCYByBliOKWw8CpDZ29ldjRvscUzSNb6fpf2VJg0LxMHHmNkkMOfbH07GijpYLnH6X4E/szTtKshqks66dqbX6ySx5d1KuojJ3dQHHzd9vTmqMfw5kji1uBLrSFXVVule5XScXYExLYMvm/MFJHG0ZCjpXfUUf1+S/RDv/X3v9Wc9oHhGx8Nape3OmJb29teQwq9rDbLGBIm4FwR6gjjHUZzya6Giihu5KVgooooGFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAYc+u6jDcSxJ4T1mdEcqssctmFcA/eG6cHB68gH1AqP8A4SHVP+hM1z/v9Zf/ACRRRQAf8JDqn/Qma5/3+sv/AJIo/wCEh1T/AKEzXP8Av9Zf/JFFFAB/wkOqf9CZrn/f6y/+SKP+Eh1T/oTNc/7/AFl/8kUUUAH/AAkOqf8AQma5/wB/rL/5Io/4SHVP+hM1z/v9Zf8AyRRRQAf8JDqn/Qma5/3+sv8A5Io/4SHVP+hM1z/v9Zf/ACRRRQAf8JDqn/Qma5/3+sv/AJIo/wCEh1T/AKEzXP8Av9Zf/JFFFAB/wkOqf9CZrn/f6y/+SKP+Eh1T/oTNc/7/AFl/8kUUUAH/AAkOqf8AQma5/wB/rL/5Io/4SHVP+hM1z/v9Zf8AyRRRQAf8JDqn/Qma5/3+sv8A5Io/4SHVP+hM1z/v9Zf/ACRRRQAf8JDqn/Qma5/3+sv/AJIo/wCEh1T/AKEzXP8Av9Zf/JFFFAB/wkOqf9CZrn/f6y/+SKP+Eh1T/oTNc/7/AFl/8kUUUAH/AAkOqf8AQma5/wB/rL/5Io/4SHVP+hM1z/v9Zf8AyRRRQAf8JDqn/Qma5/3+sv8A5Io/4SHVP+hM1z/v9Zf/ACRRRQAf8JDqn/Qma5/3+sv/AJIo/wCEh1T/AKEzXP8Av9Zf/JFFFAB/wkOqf9CZrn/f6y/+SKP+Eh1T/oTNc/7/AFl/8kUUUAH/AAkOqf8AQma5/wB/rL/5Io/4SHVP+hM1z/v9Zf8AyRRRQAf8JDqn/Qma5/3+sv8A5Io/4SHVP+hM1z/v9Zf/ACRRRQAf8JDqn/Qma5/3+sv/AJIo/wCEh1T/AKEzXP8Av9Zf/JFFFAB/wkOqf9CZrn/f6y/+SKP+Eh1T/oTNc/7/AFl/8kUUUAH/AAkOqf8AQma5/wB/rL/5Io/4SHVP+hM1z/v9Zf8AyRRRQAf8JDqn/Qma5/3+sv8A5Io/4SHVP+hM1z/v9Zf/ACRRRQAf8JDqn/Qma5/3+sv/AJIo/wCEh1T/AKEzXP8Av9Zf/JFFFAB/wkOqf9CZrn/f6y/+SKP+Eh1T/oTNc/7/AFl/8kUUUAH/AAkOqf8AQma5/wB/rL/5Io/4SHVP+hM1z/v9Zf8AyRRRQAf8JDqn/Qma5/3+sv8A5Io/4SHVP+hM1z/v9Zf/ACRRRQAf8JDqn/Qma5/3+sv/AJIo/wCEh1T/AKEzXP8Av9Zf/JFFFAFzTdVvL64aK48P6lp6BCwlupLdlJyPlHlyuc856Y4PPTJRRQB//9k=",
- "image/png": "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",
- "text/plain": [
- ""
- ]
- },
- "execution_count": 14,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "train_dataset[0]['images'][0]"
- ]
+ "7411cc7b1f224a10984238aec1967a44": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
},
- {
- "cell_type": "code",
- "execution_count": 15,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/",
- "height": 35
- },
- "id": "pdb9vErmzdAf",
- "outputId": "157008ef-e1f7-4968-d55a-eeb41906d807"
- },
- "outputs": [
- {
- "data": {
- "application/vnd.google.colaboratory.intrinsic+json": {
- "type": "string"
- },
- "text/plain": [
- "'No, the value of Favorable is not 38 in 2015. According to the chart, the value of Favorable in 2015 is 38.'"
- ]
- },
- "execution_count": 15,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "output = generate_text_from_sample(model, processor, train_dataset[0])\n",
- "output"
- ]
+ "76467e7df06e43cdb2a76c9ecc0f8c15": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
},
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "swibyq5AWctZ"
- },
- "source": [
- "Since this sample is drawn from the training set, the model has encountered it during training, which may be seen as a form of cheating. To gain a more comprehensive understanding of the model's performance, we will also evaluate it using an unseen sample.\n"
- ]
+ "76c3f48584c2454f9ac3e5756d24604f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_2e4557d45259450b9c3a84c186c9bbce",
+ "max": 5,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_b8ac9ae1610943d288ed7d8adf144304",
+ "value": 5
+ }
},
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "2fEa9ChjZsJw"
- },
- "source": []
+ "775a2d404cb94764ad3c33767237cb3d": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
},
- {
- "cell_type": "code",
- "execution_count": 16,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "czZSBgnoef1E",
- "outputId": "e9532aa4-c4cd-47d6-8c40-c4a36677ceba"
- },
- "outputs": [
- {
- "data": {
- "text/plain": [
- "[{'role': 'system',\n",
- " 'content': [{'type': 'text',\n",
- " 'text': 'You are a Vision Language Model specialized in interpreting visual data from chart images.\\nYour task is to analyze the provided chart image and respond to queries with concise answers, usually a single word, number, or short phrase.\\nThe charts include a variety of types (e.g., line charts, bar charts) and contain colors, labels, and text.\\nFocus on delivering accurate, succinct answers based on the visual information. Avoid additional explanation unless absolutely necessary.'}]},\n",
- " {'role': 'user',\n",
- " 'content': [{'type': 'image',\n",
- " 'image': },\n",
- " {'type': 'text', 'text': 'What is the value of Slovenia in the graph?'}]}]"
- ]
- },
- "execution_count": 16,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "test_dataset[10]['messages'][:2]"
- ]
+ "7c9be642c9f9452b94f8cf93e05cdc72": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
},
- {
- "cell_type": "code",
- "execution_count": 18,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/",
- "height": 617
- },
- "id": "ATuQ6ZS6eirO",
- "outputId": "df17b5b1-4c59-41da-a177-290e845d6675"
- },
- "outputs": [
- {
- "data": {
- "image/png": "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",
- "text/plain": [
- ""
- ]
- },
- "execution_count": 18,
- "metadata": {},
- "output_type": "execute_result"
- }
+ "7dece8a5ac7b4ecf91420f01d60f161b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "801d03f0db264fd58221d76b3cbc9a35": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "812420893e2d4b0f8676263f044410dc": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_9e3f26cdd0e347f2b06762128aaae329",
+ "max": 10108960,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_c99c38ec815049eaa15972ae46f94a8d",
+ "value": 10108960
+ }
+ },
+ "815589aa997046419e28fa02ad87d2dc": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_0f2fb0be37b14323be7b7ee9e9ef6e3d",
+ "IPY_MODEL_812420893e2d4b0f8676263f044410dc",
+ "IPY_MODEL_375ede44354d4b4da527d5291c8e863a"
],
- "source": [
- "test_dataset[10]['images'][0]"
- ]
+ "layout": "IPY_MODEL_b4611840b5fb433aad47e0acbdc2cd2f"
+ }
},
- {
- "cell_type": "code",
- "execution_count": 19,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/",
- "height": 35
- },
- "id": "9yHJMKHNWcMc",
- "outputId": "aae2ac9e-40aa-4981-9c74-0fd0268322a5"
- },
- "outputs": [
- {
- "data": {
- "application/vnd.google.colaboratory.intrinsic+json": {
- "type": "string"
- },
- "text/plain": [
- "'The value of Slovenia in the graph is 1.0.'"
- ]
- },
- "execution_count": 19,
- "metadata": {},
- "output_type": "execute_result"
- }
+ "81f0b09f30974d5da6d54c7495df3afb": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_319ce7779dd54087a79748cff15dd380",
+ "IPY_MODEL_bc10f7a03e1c4260b71190829160d57a",
+ "IPY_MODEL_9bf65c0fc9714cd4bbfc8b5b9ada1986"
],
- "source": [
- "output = generate_text_from_sample(model, processor, test_dataset[10])\n",
- "output"
- ]
+ "layout": "IPY_MODEL_d0106dbd65d2407da49802adca5a3f6b"
+ }
},
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "NUr6jmnAIlh1"
- },
- "source": [
- "The model has successfully learned to respond to the queries as specified in the dataset. We've achieved our goal! 🎉✨"
- ]
+ "879673e1f55640849f0ef5310c6b4b11": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
},
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "Z_Ns3p0Dhjbr"
- },
- "source": [
- "💻 I’ve developed an example application to test the model, which you can find [here](https://huggingface.co/spaces/sergiopaniego/Qwen2-VL-7B-trl-sft-ChartQA). You can easily compare it with another Space featuring the pre-trained model, available [here](https://huggingface.co/spaces/GanymedeNil/Qwen2-VL-7B)."
- ]
+ "8a732dcf3d1e4664b99b6f68df75ae17": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
},
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/",
- "height": 822
- },
- "id": "dYJJ6ASKhJ5k",
- "outputId": "f010e580-a4a1-470b-84c4-95ee999774b8"
- },
- "outputs": [
- {
- "data": {
- "text/html": [
- "\n",
- " \n",
- " "
- ],
- "text/plain": [
- ""
- ]
- },
- "execution_count": 96,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "from IPython.display import IFrame\n",
- "\n",
- "IFrame(src=\"https://sergiopaniego-qwen2-vl-7b-trl-sft-chartqa.hf.space\", width=1000, height=800)"
- ]
+ "8ad20c4edaf94518b0c3eb2d0d04b89b": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
},
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "daUMWw5xxhSc"
- },
- "source": [
- "## 6. Compare Fine-Tuned Model vs. Base Model + Prompting 📊\n",
- "\n",
- "We have explored how fine-tuning the VLM can be a valuable option for adapting it to our specific needs. Another approach to consider is directly using prompting or implementing a RAG system, which is covered in another [recipe](https://huggingface.co/learn/cookbook/multimodal_rag_using_document_retrieval_and_vlms).\n",
- "\n",
- "Fine-tuning a VLM requires significant amounts of data and computational resources, which can incur costs. In contrast, we can experiment with prompting to see if we can achieve similar results without the overhead of fine-tuning.\n",
- "\n",
- "Let's again clean up the GPU memory to ensure optimal performance 🧹"
- ]
+ "8ade50abf0714d2d921fbd74648c5004": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_4cc0e10451564ae190dbe249b15ca94d",
+ "placeholder": "",
+ "style": "IPY_MODEL_ddaddfb293174a79840350d5c5d98a3e",
+ "value": "\nPro Tip: If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. "
+ }
},
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "ei-OZGGx4lHe",
- "outputId": "81bee1a4-4860-464a-bc6a-ae2fb1695236"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "GPU allocated memory: 0.02 GB\n",
- "GPU reserved memory: 0.27 GB\n"
- ]
- }
- ],
- "source": [
- "clear_memory()"
- ]
+ "8ae0af9dc38c41cd8087dcd1e3109a7e": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
},
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "9NApMx5S4-sh"
- },
- "source": [
- "🏗️ First, we will load the baseline model following the same pipeline as before.\n"
- ]
+ "8d9cf624237b4480a2e8b430c7a5e006": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
},
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/",
- "height": 49,
- "referenced_widgets": [
- "1102501e7373424a8340e8b874ef616b",
- "a0c52a65d8d2437b8c1e679cdbde3920",
- "bd50ecadf2a942659e13e1a560d48922",
- "42906aaafe7f48b6bb4b50f08ba8eead",
- "d2a964e5096341199b0b249f1239b8a7",
- "b71d31e016d34cc7864209d1cddb90f4",
- "8ae0af9dc38c41cd8087dcd1e3109a7e",
- "8ad20c4edaf94518b0c3eb2d0d04b89b",
- "17dc54e6f66446a9941df178234a3421",
- "127ed2bd36134527beccab1ba25a86b3",
- "c0f4c16c57f941d3bfab5dcc5816194b"
- ]
- },
- "id": "VbdSklNAR1q-",
- "outputId": "a4d7d4e9-d5a2-47d2-88bb-85867f05f8fb"
- },
- "outputs": [
- {
- "data": {
- "application/vnd.jupyter.widget-view+json": {
- "model_id": "1102501e7373424a8340e8b874ef616b",
- "version_major": 2,
- "version_minor": 0
- },
- "text/plain": [
- "Loading checkpoint shards: 0%| | 0/5 [00:00},\n",
- " {'type': 'text', 'text': 'Is the value of Favorable 38 in 2015?'}]}]"
- ]
- },
- "execution_count": 93,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "train_dataset[0][:2]"
- ]
+ "92b7e089d8804be2a4f7a1e7cd82e89d": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "CheckboxModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "CheckboxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "CheckboxView",
+ "description": "Add token as git credential?",
+ "description_tooltip": null,
+ "disabled": false,
+ "indent": true,
+ "layout": "IPY_MODEL_582995cfeaf44e118d498cb7ccfd857a",
+ "style": "IPY_MODEL_8a732dcf3d1e4664b99b6f68df75ae17",
+ "value": true
+ }
},
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "fou6XKGM5Uii"
- },
- "source": [
- "Let's see how it performs!"
- ]
+ "942102ce4e974e41b2361475ca414a93": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
},
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/",
- "height": 36
- },
- "id": "eN3NkkpgR4do",
- "outputId": "5ed3fb26-580a-4c07-d626-cf8c66619b81"
- },
- "outputs": [
- {
- "data": {
- "application/vnd.google.colaboratory.intrinsic+json": {
- "type": "string"
- },
- "text/plain": [
- "'Yes'"
- ]
- },
- "execution_count": 94,
- "metadata": {},
- "output_type": "execute_result"
- }
+ "9bf65c0fc9714cd4bbfc8b5b9ada1986": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_341897caa36f49c082e98ea94d559ddb",
+ "placeholder": "",
+ "style": "IPY_MODEL_0771b04a68e7476787cd2d1e0f2ce30b",
+ "value": " 859/859 [00:00<00:00, 106kB/s]"
+ }
+ },
+ "9e3f26cdd0e347f2b06762128aaae329": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "a0c52a65d8d2437b8c1e679cdbde3920": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_b71d31e016d34cc7864209d1cddb90f4",
+ "placeholder": "",
+ "style": "IPY_MODEL_8ae0af9dc38c41cd8087dcd1e3109a7e",
+ "value": "Loading checkpoint shards: 100%"
+ }
+ },
+ "a2e17e3dcd684ac89e09de8fa4082e90": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "LabelModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "LabelModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "LabelView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_efbd24054785495f9c521b097d487b83",
+ "placeholder": "",
+ "style": "IPY_MODEL_0bf82ddbeeab48eab8f77dd8d99071c1",
+ "value": "Connecting..."
+ }
+ },
+ "a3fc798acf0848238b43b7580998e300": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "a62f4664a5ac40d785893e4eff1e34c0": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "b2ec4b8bf53245c88cb74e59612713fb": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_14de7b80d5bf46e7b900682b20d61cef",
+ "placeholder": "",
+ "style": "IPY_MODEL_10561db48a4b430e98b0e11bd8aa1ef6",
+ "value": "
Copy a token from your Hugging Face\ntokens page and paste it below.
Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file. "
+ }
+ },
+ "b45a7622ec4d4d8986305dcf6d85c0bf": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_3ab0220ff74845fbaf546603153f5cb8",
+ "IPY_MODEL_76c3f48584c2454f9ac3e5756d24604f",
+ "IPY_MODEL_f8a009ee72324c3cbe13411430c3f8fb"
],
- "source": [
- "text = processor.apply_chat_template(\n",
- " train_dataset[0][:2], tokenize=False, add_generation_prompt=True\n",
- ")\n",
- "\n",
- "image_inputs, _ = process_vision_info(train_dataset[0])\n",
- "\n",
- "inputs = processor(\n",
- " text=[text],\n",
- " images=image_inputs,\n",
- " return_tensors=\"pt\",\n",
- ")\n",
- "\n",
- "inputs = inputs.to(\"cuda\")\n",
- "\n",
- "generated_ids = model.generate(**inputs, max_new_tokens=1024)\n",
- "generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]\n",
- "\n",
- "output_text = processor.batch_decode(\n",
- " generated_ids_trimmed,\n",
- " skip_special_tokens=True,\n",
- " clean_up_tokenization_spaces=False\n",
- ")\n",
- "\n",
- "output_text[0]"
- ]
+ "layout": "IPY_MODEL_2b4f36d611ab419396c9e84c3cb8f399"
+ }
},
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "o9Id3dzV5Wwy"
- },
- "source": [
- "💡 As we can see, the model generates the correct answer using the pretrained model along with the additional system message, without any training. This approach may serve as a viable alternative to fine-tuning, depending on the specific use case."
- ]
+ "b4611840b5fb433aad47e0acbdc2cd2f": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
},
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "Wgv0-sy8TLPE"
- },
- "source": [
- "## 7. Continuing the Learning Journey 🧑🎓️\n",
- "\n",
- "To further enhance your understanding and skills in working with multimodal models, check out the following resources:\n",
- "\n",
- "- [Multimodal Retrieval-Augmented Generation (RAG) Recipe](https://huggingface.co/learn/cookbook/multimodal_rag_using_document_retrieval_and_vlms)\n",
- "- [Phil Schmid's tutorial](https://www.philschmid.de/fine-tune-multimodal-llms-with-trl)\n",
- "- [Merve Noyan's **smol-vision** repository](https://github.com/merveenoyan/smol-vision/tree/main)\n",
- "- [Quantize Your Qwen2-VL Model with AutoAWQ](https://github.com/QwenLM/Qwen2-VL?tab=readme-ov-file#quantize-your-own-model-with-autoawq)\n",
- "- [Preference Optimization for Vision Language Models with TRL](https://huggingface.co/blog/dpo_vlm)\n",
- "- [Hugging Face Llama Recipes: SFT for VLM](https://github.com/huggingface/huggingface-llama-recipes/blob/main/fine_tune/sft_vlm.py)\n",
- "- [Hugging Face Llama Recipes: PEFT Fine-Tuning](https://github.com/huggingface/huggingface-llama-recipes/blob/main/fine_tune/peft_finetuning.py)\n",
- "- [Hugging Face Blog: IDEFICS2](https://huggingface.co/blog/idefics2)\n",
- "\n",
- "These resources will help you deepen your knowledge and skills in multimodal learning.\n",
- "\n"
- ]
- }
- ],
- "metadata": {
- "accelerator": "GPU",
- "colab": {
- "gpuType": "A100",
- "machine_shape": "hm",
- "provenance": []
+ "b49628cfbdfc40b7956baa4cbf93829b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ButtonModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ButtonModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ButtonView",
+ "button_style": "",
+ "description": "Login",
+ "disabled": false,
+ "icon": "",
+ "layout": "IPY_MODEL_23d8b425314a447b8239de0b294e5db9",
+ "style": "IPY_MODEL_30c9d00326c04024a9a171a83352281b",
+ "tooltip": ""
+ }
+ },
+ "b71d31e016d34cc7864209d1cddb90f4": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "b8ac9ae1610943d288ed7d8adf144304": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "bc10f7a03e1c4260b71190829160d57a": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_775a2d404cb94764ad3c33767237cb3d",
+ "max": 859,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_905424605e68484796735ce42262b511",
+ "value": 859
+ }
+ },
+ "bd50ecadf2a942659e13e1a560d48922": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_8ad20c4edaf94518b0c3eb2d0d04b89b",
+ "max": 5,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_17dc54e6f66446a9941df178234a3421",
+ "value": 5
+ }
+ },
+ "c0f4c16c57f941d3bfab5dcc5816194b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "c264ef9a3ada4fbdbb2b7c55ecb84ed1": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "c865a38342ac4b49951d3dad4a774838": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "PasswordModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "PasswordModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "PasswordView",
+ "continuous_update": true,
+ "description": "Token:",
+ "description_tooltip": null,
+ "disabled": false,
+ "layout": "IPY_MODEL_23511e8b562e4f7e99aa2854a9d98c17",
+ "placeholder": "",
+ "style": "IPY_MODEL_76467e7df06e43cdb2a76c9ecc0f8c15",
+ "value": ""
+ }
+ },
+ "c99c38ec815049eaa15972ae46f94a8d": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
},
- "kernelspec": {
- "display_name": "Python 3",
- "name": "python3"
+ "cdfde68c4fbf4d7c9bb44ce31bfdf243": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
},
- "language_info": {
- "name": "python"
+ "d0106dbd65d2407da49802adca5a3f6b": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
},
- "widgets": {
- "application/vnd.jupyter.widget-state+json": {
- "03cfe58d482440f3bf80afc43e53730a": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "0771b04a68e7476787cd2d1e0f2ce30b": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "DescriptionStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- },
- "0bf82ddbeeab48eab8f77dd8d99071c1": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "DescriptionStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- },
- "0f2fb0be37b14323be7b7ee9e9ef6e3d": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HTMLModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HTMLModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HTMLView",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_03cfe58d482440f3bf80afc43e53730a",
- "placeholder": "",
- "style": "IPY_MODEL_801d03f0db264fd58221d76b3cbc9a35",
- "value": "adapter_model.safetensors: 100%"
- }
- },
- "10561db48a4b430e98b0e11bd8aa1ef6": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "DescriptionStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- },
- "1102501e7373424a8340e8b874ef616b": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HBoxModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HBoxModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HBoxView",
- "box_style": "",
- "children": [
- "IPY_MODEL_a0c52a65d8d2437b8c1e679cdbde3920",
- "IPY_MODEL_bd50ecadf2a942659e13e1a560d48922",
- "IPY_MODEL_42906aaafe7f48b6bb4b50f08ba8eead"
- ],
- "layout": "IPY_MODEL_d2a964e5096341199b0b249f1239b8a7"
- }
- },
- "127ed2bd36134527beccab1ba25a86b3": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "14de7b80d5bf46e7b900682b20d61cef": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "174ecb5e6cd54b2989887e08f7b7ac04": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "FloatProgressModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "FloatProgressModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "ProgressView",
- "bar_style": "success",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_d0e8e5e0352448ff9266f06b9f97b092",
- "max": 10107280,
- "min": 0,
- "orientation": "horizontal",
- "style": "IPY_MODEL_7dece8a5ac7b4ecf91420f01d60f161b",
- "value": 10107280
- }
- },
- "17dc54e6f66446a9941df178234a3421": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "ProgressStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "ProgressStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "bar_color": null,
- "description_width": ""
- }
- },
- "1aa67fff82344f299f5c73a419871b03": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "DescriptionStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- },
- "1aac4bfb05c14e42a3f4372fc535ece6": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "FloatProgressModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "FloatProgressModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "ProgressView",
- "bar_style": "success",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_8f940de2b7ff49ecb05257990b335eed",
- "max": 5,
- "min": 0,
- "orientation": "horizontal",
- "style": "IPY_MODEL_cdfde68c4fbf4d7c9bb44ce31bfdf243",
- "value": 5
- }
- },
- "23511e8b562e4f7e99aa2854a9d98c17": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "23d8b425314a447b8239de0b294e5db9": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "27d3420d65a545e29cbdae604caa32f3": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HBoxModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HBoxModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HBoxView",
- "box_style": "",
- "children": [
- "IPY_MODEL_37925f7df7324bcb8f7d07389730cf82",
- "IPY_MODEL_174ecb5e6cd54b2989887e08f7b7ac04",
- "IPY_MODEL_3b50f08adb95437ead16c8303c971470"
- ],
- "layout": "IPY_MODEL_8d9cf624237b4480a2e8b430c7a5e006"
- }
- },
- "2b4f36d611ab419396c9e84c3cb8f399": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "2d4e5b7585a0441ca4eacec3a2ac7785": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "DescriptionStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- },
- "2e4557d45259450b9c3a84c186c9bbce": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "30c9d00326c04024a9a171a83352281b": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "ButtonStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "ButtonStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "button_color": null,
- "font_weight": ""
- }
- },
- "319ce7779dd54087a79748cff15dd380": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HTMLModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HTMLModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HTMLView",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_5d1335feb15d470eb70727f1fc85fc64",
- "placeholder": "",
- "style": "IPY_MODEL_5b0be6b9dfc046769a90b0167faa9023",
- "value": "adapter_config.json: 100%"
- }
- },
- "31be17b18a5e48b498bd009692f4a2d6": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "32f97bb4d25d4d32958d35ac3e897ab9": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "DescriptionStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- },
- "341897caa36f49c082e98ea94d559ddb": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "375ede44354d4b4da527d5291c8e863a": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HTMLModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HTMLModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HTMLView",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_a62f4664a5ac40d785893e4eff1e34c0",
- "placeholder": "",
- "style": "IPY_MODEL_1aa67fff82344f299f5c73a419871b03",
- "value": " 10.1M/10.1M [00:00<00:00, 10.4MB/s]"
- }
- },
- "37925f7df7324bcb8f7d07389730cf82": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HTMLModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HTMLModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HTMLView",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_31be17b18a5e48b498bd009692f4a2d6",
- "placeholder": "",
- "style": "IPY_MODEL_dfa21476037b465b9e2143d027433f40",
- "value": "adapter_model.safetensors: 100%"
- }
- },
- "3ab0220ff74845fbaf546603153f5cb8": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HTMLModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HTMLModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HTMLView",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_e7cbc93b8a284c98bc1e1b1462d9cfb2",
- "placeholder": "",
- "style": "IPY_MODEL_942102ce4e974e41b2361475ca414a93",
- "value": "Loading checkpoint shards: 100%"
- }
- },
- "3b50f08adb95437ead16c8303c971470": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HTMLModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HTMLModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HTMLView",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_e525f59c59f74a2c97ab8a72786127ed",
- "placeholder": "",
- "style": "IPY_MODEL_32f97bb4d25d4d32958d35ac3e897ab9",
- "value": " 10.1M/10.1M [00:00<00:00, 26.1MB/s]"
- }
- },
- "3d7dbcc18c1b4dceae74bdfb75a8da8e": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "VBoxModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "VBoxModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "VBoxView",
- "box_style": "",
- "children": [],
- "layout": "IPY_MODEL_fcb2f724d1ad4157b907d48fa993efd4"
- }
- },
- "42906aaafe7f48b6bb4b50f08ba8eead": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HTMLModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HTMLModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HTMLView",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_127ed2bd36134527beccab1ba25a86b3",
- "placeholder": "",
- "style": "IPY_MODEL_c0f4c16c57f941d3bfab5dcc5816194b",
- "value": " 5/5 [00:06<00:00, 1.24s/it]"
- }
- },
- "4cc0e10451564ae190dbe249b15ca94d": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "582995cfeaf44e118d498cb7ccfd857a": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "5b0be6b9dfc046769a90b0167faa9023": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "DescriptionStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- },
- "5d1335feb15d470eb70727f1fc85fc64": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "63e7a6485906469aa9b709f3b119f9be": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HTMLModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HTMLModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HTMLView",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_ee59471ae1ef4182a04260ef870a5fae",
- "placeholder": "",
- "style": "IPY_MODEL_2d4e5b7585a0441ca4eacec3a2ac7785",
- "value": "Loading checkpoint shards: 100%"
- }
- },
- "6d358c3999024558bbdf63cc8ff3b0c8": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HBoxModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HBoxModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HBoxView",
- "box_style": "",
- "children": [
- "IPY_MODEL_63e7a6485906469aa9b709f3b119f9be",
- "IPY_MODEL_1aac4bfb05c14e42a3f4372fc535ece6",
- "IPY_MODEL_fc3de4763c3f462785f4cde31c35c68e"
- ],
- "layout": "IPY_MODEL_7411cc7b1f224a10984238aec1967a44"
- }
- },
- "7411cc7b1f224a10984238aec1967a44": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "76467e7df06e43cdb2a76c9ecc0f8c15": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "DescriptionStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- },
- "76c3f48584c2454f9ac3e5756d24604f": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "FloatProgressModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "FloatProgressModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "ProgressView",
- "bar_style": "success",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_2e4557d45259450b9c3a84c186c9bbce",
- "max": 5,
- "min": 0,
- "orientation": "horizontal",
- "style": "IPY_MODEL_b8ac9ae1610943d288ed7d8adf144304",
- "value": 5
- }
- },
- "775a2d404cb94764ad3c33767237cb3d": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "7c9be642c9f9452b94f8cf93e05cdc72": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "7dece8a5ac7b4ecf91420f01d60f161b": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "ProgressStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "ProgressStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "bar_color": null,
- "description_width": ""
- }
- },
- "801d03f0db264fd58221d76b3cbc9a35": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "DescriptionStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- },
- "812420893e2d4b0f8676263f044410dc": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "FloatProgressModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "FloatProgressModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "ProgressView",
- "bar_style": "success",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_9e3f26cdd0e347f2b06762128aaae329",
- "max": 10108960,
- "min": 0,
- "orientation": "horizontal",
- "style": "IPY_MODEL_c99c38ec815049eaa15972ae46f94a8d",
- "value": 10108960
- }
- },
- "815589aa997046419e28fa02ad87d2dc": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HBoxModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HBoxModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HBoxView",
- "box_style": "",
- "children": [
- "IPY_MODEL_0f2fb0be37b14323be7b7ee9e9ef6e3d",
- "IPY_MODEL_812420893e2d4b0f8676263f044410dc",
- "IPY_MODEL_375ede44354d4b4da527d5291c8e863a"
- ],
- "layout": "IPY_MODEL_b4611840b5fb433aad47e0acbdc2cd2f"
- }
- },
- "81f0b09f30974d5da6d54c7495df3afb": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HBoxModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HBoxModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HBoxView",
- "box_style": "",
- "children": [
- "IPY_MODEL_319ce7779dd54087a79748cff15dd380",
- "IPY_MODEL_bc10f7a03e1c4260b71190829160d57a",
- "IPY_MODEL_9bf65c0fc9714cd4bbfc8b5b9ada1986"
- ],
- "layout": "IPY_MODEL_d0106dbd65d2407da49802adca5a3f6b"
- }
- },
- "879673e1f55640849f0ef5310c6b4b11": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "DescriptionStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- },
- "8a732dcf3d1e4664b99b6f68df75ae17": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "DescriptionStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- },
- "8ad20c4edaf94518b0c3eb2d0d04b89b": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "8ade50abf0714d2d921fbd74648c5004": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HTMLModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HTMLModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HTMLView",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_4cc0e10451564ae190dbe249b15ca94d",
- "placeholder": "",
- "style": "IPY_MODEL_ddaddfb293174a79840350d5c5d98a3e",
- "value": "\nPro Tip: If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. "
- }
- },
- "8ae0af9dc38c41cd8087dcd1e3109a7e": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "DescriptionStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- },
- "8d9cf624237b4480a2e8b430c7a5e006": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "8f940de2b7ff49ecb05257990b335eed": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "905424605e68484796735ce42262b511": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "ProgressStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "ProgressStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "bar_color": null,
- "description_width": ""
- }
- },
- "92b7e089d8804be2a4f7a1e7cd82e89d": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "CheckboxModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "CheckboxModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "CheckboxView",
- "description": "Add token as git credential?",
- "description_tooltip": null,
- "disabled": false,
- "indent": true,
- "layout": "IPY_MODEL_582995cfeaf44e118d498cb7ccfd857a",
- "style": "IPY_MODEL_8a732dcf3d1e4664b99b6f68df75ae17",
- "value": true
- }
- },
- "942102ce4e974e41b2361475ca414a93": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "DescriptionStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- },
- "9bf65c0fc9714cd4bbfc8b5b9ada1986": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HTMLModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HTMLModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HTMLView",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_341897caa36f49c082e98ea94d559ddb",
- "placeholder": "",
- "style": "IPY_MODEL_0771b04a68e7476787cd2d1e0f2ce30b",
- "value": " 859/859 [00:00<00:00, 106kB/s]"
- }
- },
- "9e3f26cdd0e347f2b06762128aaae329": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "a0c52a65d8d2437b8c1e679cdbde3920": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HTMLModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HTMLModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HTMLView",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_b71d31e016d34cc7864209d1cddb90f4",
- "placeholder": "",
- "style": "IPY_MODEL_8ae0af9dc38c41cd8087dcd1e3109a7e",
- "value": "Loading checkpoint shards: 100%"
- }
- },
- "a2e17e3dcd684ac89e09de8fa4082e90": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "LabelModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "LabelModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "LabelView",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_efbd24054785495f9c521b097d487b83",
- "placeholder": "",
- "style": "IPY_MODEL_0bf82ddbeeab48eab8f77dd8d99071c1",
- "value": "Connecting..."
- }
- },
- "a3fc798acf0848238b43b7580998e300": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "DescriptionStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- },
- "a62f4664a5ac40d785893e4eff1e34c0": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "b2ec4b8bf53245c88cb74e59612713fb": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HTMLModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HTMLModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HTMLView",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_14de7b80d5bf46e7b900682b20d61cef",
- "placeholder": "",
- "style": "IPY_MODEL_10561db48a4b430e98b0e11bd8aa1ef6",
- "value": "
Copy a token from your Hugging Face\ntokens page and paste it below.
Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file. "
- }
- },
- "b45a7622ec4d4d8986305dcf6d85c0bf": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HBoxModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HBoxModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HBoxView",
- "box_style": "",
- "children": [
- "IPY_MODEL_3ab0220ff74845fbaf546603153f5cb8",
- "IPY_MODEL_76c3f48584c2454f9ac3e5756d24604f",
- "IPY_MODEL_f8a009ee72324c3cbe13411430c3f8fb"
- ],
- "layout": "IPY_MODEL_2b4f36d611ab419396c9e84c3cb8f399"
- }
- },
- "b4611840b5fb433aad47e0acbdc2cd2f": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "b49628cfbdfc40b7956baa4cbf93829b": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "ButtonModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "ButtonModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "ButtonView",
- "button_style": "",
- "description": "Login",
- "disabled": false,
- "icon": "",
- "layout": "IPY_MODEL_23d8b425314a447b8239de0b294e5db9",
- "style": "IPY_MODEL_30c9d00326c04024a9a171a83352281b",
- "tooltip": ""
- }
- },
- "b71d31e016d34cc7864209d1cddb90f4": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "b8ac9ae1610943d288ed7d8adf144304": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "ProgressStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "ProgressStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "bar_color": null,
- "description_width": ""
- }
- },
- "bc10f7a03e1c4260b71190829160d57a": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "FloatProgressModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "FloatProgressModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "ProgressView",
- "bar_style": "success",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_775a2d404cb94764ad3c33767237cb3d",
- "max": 859,
- "min": 0,
- "orientation": "horizontal",
- "style": "IPY_MODEL_905424605e68484796735ce42262b511",
- "value": 859
- }
- },
- "bd50ecadf2a942659e13e1a560d48922": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "FloatProgressModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "FloatProgressModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "ProgressView",
- "bar_style": "success",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_8ad20c4edaf94518b0c3eb2d0d04b89b",
- "max": 5,
- "min": 0,
- "orientation": "horizontal",
- "style": "IPY_MODEL_17dc54e6f66446a9941df178234a3421",
- "value": 5
- }
- },
- "c0f4c16c57f941d3bfab5dcc5816194b": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "DescriptionStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- },
- "c264ef9a3ada4fbdbb2b7c55ecb84ed1": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "c865a38342ac4b49951d3dad4a774838": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "PasswordModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "PasswordModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "PasswordView",
- "continuous_update": true,
- "description": "Token:",
- "description_tooltip": null,
- "disabled": false,
- "layout": "IPY_MODEL_23511e8b562e4f7e99aa2854a9d98c17",
- "placeholder": "",
- "style": "IPY_MODEL_76467e7df06e43cdb2a76c9ecc0f8c15",
- "value": ""
- }
- },
- "c99c38ec815049eaa15972ae46f94a8d": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "ProgressStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "ProgressStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "bar_color": null,
- "description_width": ""
- }
- },
- "cdfde68c4fbf4d7c9bb44ce31bfdf243": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "ProgressStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "ProgressStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "bar_color": null,
- "description_width": ""
- }
- },
- "d0106dbd65d2407da49802adca5a3f6b": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "d0e8e5e0352448ff9266f06b9f97b092": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "d2a964e5096341199b0b249f1239b8a7": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "ddaddfb293174a79840350d5c5d98a3e": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "DescriptionStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- },
- "dfa21476037b465b9e2143d027433f40": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "DescriptionStyleModel",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- },
- "e525f59c59f74a2c97ab8a72786127ed": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "e7cbc93b8a284c98bc1e1b1462d9cfb2": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "ee59471ae1ef4182a04260ef870a5fae": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "efbd24054785495f9c521b097d487b83": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": null,
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": null,
- "flex": null,
- "flex_flow": null,
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": null
- }
- },
- "f8a009ee72324c3cbe13411430c3f8fb": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HTMLModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HTMLModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HTMLView",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_7c9be642c9f9452b94f8cf93e05cdc72",
- "placeholder": "",
- "style": "IPY_MODEL_879673e1f55640849f0ef5310c6b4b11",
- "value": " 5/5 [00:17<00:00, 3.00s/it]"
- }
- },
- "fc3de4763c3f462785f4cde31c35c68e": {
- "model_module": "@jupyter-widgets/controls",
- "model_module_version": "1.5.0",
- "model_name": "HTMLModel",
- "state": {
- "_dom_classes": [],
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "HTMLModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/controls",
- "_view_module_version": "1.5.0",
- "_view_name": "HTMLView",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_c264ef9a3ada4fbdbb2b7c55ecb84ed1",
- "placeholder": "",
- "style": "IPY_MODEL_a3fc798acf0848238b43b7580998e300",
- "value": " 5/5 [00:04<00:00, 1.23it/s]"
- }
- },
- "fcb2f724d1ad4157b907d48fa993efd4": {
- "model_module": "@jupyter-widgets/base",
- "model_module_version": "1.2.0",
- "model_name": "LayoutModel",
- "state": {
- "_model_module": "@jupyter-widgets/base",
- "_model_module_version": "1.2.0",
- "_model_name": "LayoutModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "LayoutView",
- "align_content": null,
- "align_items": "center",
- "align_self": null,
- "border": null,
- "bottom": null,
- "display": "flex",
- "flex": null,
- "flex_flow": "column",
- "grid_area": null,
- "grid_auto_columns": null,
- "grid_auto_flow": null,
- "grid_auto_rows": null,
- "grid_column": null,
- "grid_gap": null,
- "grid_row": null,
- "grid_template_areas": null,
- "grid_template_columns": null,
- "grid_template_rows": null,
- "height": null,
- "justify_content": null,
- "justify_items": null,
- "left": null,
- "margin": null,
- "max_height": null,
- "max_width": null,
- "min_height": null,
- "min_width": null,
- "object_fit": null,
- "object_position": null,
- "order": null,
- "overflow": null,
- "overflow_x": null,
- "overflow_y": null,
- "padding": null,
- "right": null,
- "top": null,
- "visibility": null,
- "width": "50%"
- }
- }
- }
+ "d0e8e5e0352448ff9266f06b9f97b092": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "d2a964e5096341199b0b249f1239b8a7": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "ddaddfb293174a79840350d5c5d98a3e": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "dfa21476037b465b9e2143d027433f40": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "e525f59c59f74a2c97ab8a72786127ed": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "e7cbc93b8a284c98bc1e1b1462d9cfb2": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "ee59471ae1ef4182a04260ef870a5fae": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "efbd24054785495f9c521b097d487b83": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "f8a009ee72324c3cbe13411430c3f8fb": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_7c9be642c9f9452b94f8cf93e05cdc72",
+ "placeholder": "",
+ "style": "IPY_MODEL_879673e1f55640849f0ef5310c6b4b11",
+ "value": " 5/5 [00:17<00:00, 3.00s/it]"
+ }
+ },
+ "fc3de4763c3f462785f4cde31c35c68e": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_c264ef9a3ada4fbdbb2b7c55ecb84ed1",
+ "placeholder": "",
+ "style": "IPY_MODEL_a3fc798acf0848238b43b7580998e300",
+ "value": " 5/5 [00:04<00:00, 1.23it/s]"
+ }
+ },
+ "fcb2f724d1ad4157b907d48fa993efd4": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": "center",
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": "flex",
+ "flex": null,
+ "flex_flow": "column",
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": "50%"
+ }
}
- },
- "nbformat": 4,
- "nbformat_minor": 0
+ }
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
}