[Model Request] gorilla-llm/gorilla-openfunctions-v2 (7B model with functional calling performance is On-par with GPT-4)

[t83714]

⚙️ Request New Models

• Link to an existing implementation (e.g. Hugging Face/Github): https://huggingface.co/gorilla-llm/gorilla-openfunctions-v2
  • Why? With 7B size, the functional calling performance is On-par with GPT-4 See BFCL leaderboard
• Is this model architecture supported by MLC-LLM? Yes. the config.json states LlamaForCausalLM

Additional context