gorilla
gorilla copied to clipboard
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
# Description As we continue to enhance the development process of our repository, it's essential to ensure code quality and consistency. This issue aims to implement an automated GitHub Workflow...
When running the falcon model, after the user prompt, the model response is prefixed with this warning. ``` The attention mask and the pad token id were not set. As...
Hi @ShishirPatil @eltociear, [We](https://github.com/BerriAI/litellm) built a hosted UI playground for people to compare Gorilla's LLM to GPT-4 and Claude-2 Adding a link to it so people can easily test Gorilla!
@ShishirPatil want to make proper code formatting
Hi, I am interested in this project and I have done some reasearch. I tried the evaluation on the TorchHub API senerio with some of the latest models and other...
This PR adds support for models from all the above mentioned providers using litellm https://github.com/BerriAI/litellm TLDR: gorilla gets: - more models out of the box, everything litellm integrates with: https://litellm.readthedocs.io/en/latest/supported/...
Gorilla often recommends slightly changed recommendations, apparently randomly, and provides no visibility of commands successfully used in the past(or even that the command was recommended prior). Having context on the...
It is unclear exactly what the commands gorilla will intereract with, where they come from, and why. The system should format(possibly using a flag) detaileds description and systems/dependencies interacted with,...
Great work thanks for sharing!!! I used the fastchat code combined with the apibench/huggingface_train.json data and the llamav2-7b model to retrain to get a new model, but the inference result...