GH Repository · ShishirPatil
gorilla
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
- stars
- 13,028
- 30-day movement
- +41/day
- Related entries
- 60
- Connections
- 2
Pythonopenai-apiothergpt-4-apichatgptclaude-apiapi-documentationopenai-functionsllmapi
Gorilla is a research project for training and evaluating LLMs on function (tool) calls, per its own title. The repository is Python-based, Apache-2.0 licensed, and ships a devcontainer; the recorded material does not list its concrete tools or datasets.
Reach for it when you want an open, Apache-2.0 starting point for LLM function-calling training and evaluation work.
Use it to
- Train models to make API function calls
- Evaluate tool-calling accuracy of LLMs
- Explore API-benchmarking research code in a devcontainer
- Reuse its evaluation harness for your own function-call tests
For Researchers and engineers working on LLM tool calling
- Role
- other
- Language
- Python
- Licence
- Apache-2.0
- Forks
- 1,406
- Open issues
- 163
- Last push
- 2026-04-13
- Latest release
- v0.0.1 · 2023-07-18
topicsllmfunction-callingapievaluationtrainingopen-source