gorilla
gorilla copied to clipboard
ShishirPatil
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
Is there a reson to use ```questions_torchhub_0_shot.jsonl``` instead of ```questions_torchhub_bm25.jsonl``` when evaluating the retriever with torchub. This is what is mentioned in the documentation for evaluation script. The arguments seem...
Note that pickle is not secure (see https://docs.python.org/3/library/pickle.html) and can lead to remote code execution: https://github.com/ShishirPatil/gorilla/blob/a3e7b2c2a65a4d21c44a144b8cc7c0bc7ab8c7eb/goex/function/slack_read_messages.py#L13 Loading the tokens from an alternative file format such as JSON would be safer,...
This project provides a web application for fetching API calls from a API documentation urls into a specified format (Option 1), to easily generate training points to train a fine-tuned...
This PR adds support for a GitHub Codespaces Dev Container for the `goex` sub-project: - Designed to allow adding Codespaces configurations for other sub projects - Dev Container config `GoEX`...
# Summary This PR introduces a new model handler [openfunctions_handler.py](https://github.com/ShishirPatil/gorilla/compare/main...JasonZhu1313:gorilla:jaszhu/add_openfunctions_handler?expand=1#diff-3af430d47eb913aec657f3bad6dcbae4e39ee152dcb8b1699e65614fdd87e10d) to run inference on OS model gorilla-llm/gorilla-openfunctions-v2 and reproduce the results on leaderboard Issue: https://github.com/ShishirPatil/gorilla/issues/352 # Changes * Merge the...
**Describe the bug** A clear and concise description of what the bug is. Great work on gorilla! I have used the OS model checkpoint https://huggingface.co/gorilla-llm/gorilla-openfunctions-v2 with vLLM to try reproducing...
Hello, I would like to ask how many pieces of data were used as training sets during the fine-tuning process of the RAFT paper?
**Describe the bug** when I run RAFT： ` python3 raft.py --datapath sample_data/United_States_PDF.pdf --output ./sample_ds4 --distractors 4 --doctype pdf --chunk_size 512 --questions 5 --openai_key OPENAI_KEY` there is an error： ``` Traceback...
In inference_local.py, get_prompt func just supports single query, so how to get prompt for multiturn conversation? ``` def get_prompt(user_query: str, functions: list = []) -> str: """ Generates a conversation...
Hi team, Your project requires to set up the base_url to evaluate the fine-tuned model. Can you tell me how to find this in the Azure AI Studio? Sincerely, Zhangcheng...
Metadata
Owner
Metadata
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)