marclove/llama-2-7b-chat-functions
marclove/llama-2-7b-chat-functions is a 7 billion parameter Llama-2-7b-chat-hf model, further fine-tuned by Marc Love. This model specializes in generating synthetic OpenAPI function calls from natural language, while also maintaining general chat capabilities. It is designed for developers exploring function calling mechanisms in smaller language models, offering a balance between structured output generation and conversational interaction.
Loading preview...
Overview
marclove/llama-2-7b-chat-functions is a 7 billion parameter model, fine-tuned by Marc Love from the base Llama-2-7b-chat-hf model. Its unique training regimen involves a 50/50 mix of synthetic OpenAPI function calls paired with natural language invocations, and chat completions from the Guanaco subset of the OASST1 dataset. This dual-dataset approach aims to balance function calling accuracy with general chat model helpfulness.
Key Capabilities
- Function Calling: Generates structured OpenAPI function calls based on natural language prompts.
- Chat Completions: Retains general conversational abilities for non-function-calling scenarios.
- Beta State: Currently in beta, with future updates planned to improve performance and potentially modify the prompting format.
Good For
- Research and Development: Ideal for exploring and experimenting with function calling capabilities in smaller LLMs.
- Prototyping: Useful for quickly prototyping applications that require models to interact with external tools via function calls.
- Validation: Users are encouraged to validate all function call outputs due to potential hallucinations, especially in the 7B model. Tools like Pydantic are suggested for validation.