Mistral-Nemo-Instruct-2407 [Model Request]

[electroglyph]

⚙️ Request New Models

• Link to an existing implementation (e.g. Hugging Face/Github): https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407
• Is this model architecture supported by MLC-LLM? (the list of supported models) No, needs RoPE support and has custom tokenizer

here's what llama.cpp tokenizer update looked like:

m18coppola/llama.cpp@7fc8505

[yyjhao]

seems to work by just disabling an assertion: #2676