Skip to content

Removed Obsolete ModelParams Constructor #312

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 18, 2023
Merged

Removed Obsolete ModelParams Constructor #312

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 0 additions & 48 deletions LLama/Common/ModelParams.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,54 +111,6 @@ private ModelParams()
// This constructor (default parameterless constructor) is used by Newtonsoft to deserialize!
ModelPath = "";
}

/// <summary>
///
/// </summary>
/// <param name="modelPath">The model path.</param>
/// <param name="contextSize">Model context size (n_ctx)</param>
/// <param name="gpuLayerCount">Number of layers to run in VRAM / GPU memory (n_gpu_layers)</param>
/// <param name="seed">Seed for the random number generator (seed)</param>
/// <param name="useFp16Memory">Whether to use f16 instead of f32 for memory kv (memory_f16)</param>
/// <param name="useMemorymap">Whether to use mmap for faster loads (use_mmap)</param>
/// <param name="useMemoryLock">Whether to use mlock to keep model in memory (use_mlock)</param>
/// <param name="perplexity">Thether to compute perplexity over the prompt (perplexity)</param>
/// <param name="loraAdapter">Lora adapter path (lora_adapter)</param>
/// <param name="loraBase">Base model path for the lora adapter (lora_base)</param>
/// <param name="threads">Number of threads (-1 = autodetect) (n_threads)</param>
/// <param name="batchSize">Batch size for prompt processing (must be >=32 to use BLAS) (n_batch)</param>
/// <param name="embeddingMode">Whether to use embedding mode. (embedding) Note that if this is set to true, The LLamaModel won't produce text response anymore.</param>
/// <param name="ropeFrequencyBase">RoPE base frequency.</param>
/// <param name="ropeFrequencyScale">RoPE frequency scaling factor</param>
/// <param name="mulMatQ">Use experimental mul_mat_q kernels</param>
/// <param name="encoding">The encoding to use to convert text for the model</param>
[Obsolete("Use object initializer to set all optional parameters")]
public ModelParams(string modelPath, uint contextSize = 512, int gpuLayerCount = 20,
uint seed = 1337, bool useFp16Memory = true,
bool useMemorymap = true, bool useMemoryLock = false, bool perplexity = false,
string loraAdapter = "", string loraBase = "", int threads = -1, uint batchSize = 512,
bool embeddingMode = false,
float? ropeFrequencyBase = null, float? ropeFrequencyScale = null, bool mulMatQ = false,
string encoding = "UTF-8")
{
ContextSize = contextSize;
GpuLayerCount = gpuLayerCount;
Seed = seed;
UseFp16Memory = useFp16Memory;
UseMemorymap = useMemorymap;
UseMemoryLock = useMemoryLock;
Perplexity = perplexity;
ModelPath = modelPath;
LoraBase = loraBase;
Threads = threads < 1 ? null : (uint)threads;
BatchSize = batchSize;
EmbeddingMode = embeddingMode;
RopeFrequencyBase = ropeFrequencyBase;
RopeFrequencyScale = ropeFrequencyScale;
MulMatQ = mulMatQ;
Encoding = Encoding.GetEncoding(encoding);
LoraAdapters.Add(new LoraAdapter(loraAdapter, 1));
}
}

internal class EncodingConverter
Expand Down