gorilla-llm/gorilla-7b-hf-delta-v0
gorilla-llm/gorilla-7b-hf-delta-v0 is a 7 billion parameter auto-regressive language model developed by Gorilla LLM (UC Berkeley), fine-tuned from LLaMA weights. This model specializes in enabling Large Language Models to interact with external tools by generating semantically and syntactically correct API calls. It is specifically trained to reliably use Hugging Face APIs, reducing hallucination in API invocation for over 1,600 APIs.
Loading preview...
Gorilla: API-Calling LLM
Gorilla is a 7 billion parameter language model, fine-tuned from LLaMA, designed to enable Large Language Models (LLMs) to interact with external tools and APIs. Developed by Gorilla LLM (UC Berkeley), this model excels at generating accurate API calls from natural language queries, significantly reducing hallucination often seen in tool-use scenarios.
Key Capabilities
- API Invocation: Translates natural language into semantically and syntactically correct API calls.
- Reduced Hallucination: Demonstrates high reliability in invoking over 1,600 APIs.
- Hugging Face API Specialization: The
gorilla-7b-hf-delta-v0variant is specifically fine-tuned for reliable use with Hugging Face APIs. - Retriever-Aware Training: Can be trained using a novel retriever-aware pipeline or standard fine-tuning.
Use Cases
- Automated Tool Use: Ideal for applications requiring LLMs to interact with external services and databases via APIs.
- Developer Assistance: Can help developers quickly generate API calls based on natural language descriptions.
- Expanding LLM Functionality: Enables LLMs to perform tasks beyond their core language generation capabilities by leveraging external tools.