gorilla-openfunctions-v2-q4f32_1-MLC
This is the gorilla-openfunctions-v2 model in MLC format q4f32_1.
The model can be used for projects MLC-LLM and WebLLM.
Example Usage
Here are some examples of using this model in MLC LLM. Before running the examples, please install MLC LLM by following the installation documentation.
Gorilla OpenFunctions v2
💡 SoTA for open-source models. On-par with GPT-4.
🚀 Check out the Berkeley Function Calling Leaderboard
📣 Read more in our OpenFunctions v2 release blog and Berkeley Function Calling Leaderboard blog
🟢 Check out Quantized GGUF models in gorilla-llm/gorilla-openfunctions-v2-gguf
Introduction
Gorilla OpenFunctions extends Large Language Model(LLM) Chat Completion feature to formulate executable APIs call given natural language instructions and API context. With OpenFunctions v2, we now support:
- Multiple functions - choose betwen functions
- Parallel functions - call the same function
Ntime with different parameter values - Multiple & parallel - both of the above in a single chatcompletion call (one generation)
- Relevance detection - when chatting, chat. When asked for function, returns a function
- Python - supports
string, number, boolean, list, tuple, dictparameter datatypes andAnyfor those not natively supported. - JAVA - support for
byte, short, int, float, double, long, boolean, char, Array, ArrayList, Set, HashMap, Hashtable, Queue, Stack, and Anydatatypes. - JavaScript - support for
String, Number, Bigint, Boolean, dict (object), Array, Date, and Anydatatypes. - REST - native REST support
Performance
| Model | Overall Accuracy* |
|---|---|
| GPT-4-0125-Preview | 85.12% |
| Gorilla-openfunctions-v2 | 83.67% |
| GPT-3.5-turbo | 82.23% |
| Mistral-medium | 79.70% |
| Nexusflow Raven-v2 | 55.72% |
| GPT-4-0613 | 54.16% |
| *: Overall Accuracy is defined in Berkeley Function Calling Leaderboard blog, read more details if you are interested! |
Models Available
| Model | Functionality |
|---|---|
| gorilla-openfunctions-v2 | Multiple, parallel, multiple & parallel, relevance detection, Python + JAVA + JS + REST |
| gorilla-openfunctions-v1 | Parallel functions, and can choose between functions |
| gorilla-openfunctions-v0 | Given a function, and user intent, returns properly formatted json with the right arguments |
All of our models are hosted on our Huggingface UC Berkeley gorilla-llm org: gorilla-openfunctions-v2, gorilla-openfunctions-v1, and gorilla-openfunctions-v0.
Training
Gorilla Openfunctions v2 is a 7B parameter model, and is built on top of the deepseek coder LLM. Check out openfunctions-v2 blog to learn more about the data composition and some insights into the training process.
Documentation
For more information on MLC LLM project, please visit our documentation and GitHub repo.
License
Gorilla OpenFunctions v2 is distributed under the Apache 2.0 license. This software incorporates elements from the Deepseek model. Consequently, the licensing of Gorilla OpenFunctions v2 adheres to the Apache 2.0 license, with additional terms as outlined in Appendix A of the Deepseek license.
Contributing
Gorilla is an open source effort from UC Berkeley and we welcome contributors. Please email us your comments, criticism, and questions. More information about the project can be found at https://gorilla.cs.berkeley.edu/