svjack / CodeActAgent-Mistral-7b-v0.1

🤖 This is a repo copy from https://huggingface.co/xingyaoww/CodeActAgent-Mistral-7b-v0.1

Below is the Github repo made by me to use the model in simple way in Gradio 😊

😊 Github Repo: https://github.com/svjack/CodeActAgent-Gradio

Executable Code Actions Elicit Better LLM Agents

💻 Code • 📃 Paper • 🤗 Data (CodeActInstruct) • 🤗 Model (CodeActAgent-Mistral-7b-v0.1) • 🤖 Chat with CodeActAgent!

We propose to use executable Python code to consolidate LLM agents’ act ions into a unified action space ( CodeAct ). Integrated with a Python interpreter, CodeAct can execute code actions and dynamically revise prior actions or emit new actions upon new observations (e.g., code execution results) through multi-turn interactions.

Why CodeAct?

Our extensive analysis of 17 LLMs on API-Bank and a newly curated benchmark M ³ ToolEval shows that CodeAct outperforms widely used alternatives like Text and JSON (up to 20% higher success rate). Please check our paper for more detailed analysis!

Comparison between CodeAct and Text / JSON as action.

Quantitative results comparing CodeAct and {Text, JSON} on M ³ ToolEval.

📁 CodeActInstruct

We collect an instruction-tuning dataset CodeActInstruct that consists of 7k multi-turn interactions using CodeAct. Dataset is release at huggingface dataset 🤗 . Please refer to the paper and this section for details of data collection.

Dataset Statistics. Token statistics are computed using Llama-2 tokenizer.

🪄 CodeActAgent

Trained on CodeActInstruct and general conversaions, CodeActAgent excels at out-of-domain agent tasks compared to open-source models of the same size, while not sacrificing generic performance (e.g., knowledge, dialog). We release two variants of CodeActAgent:

• CodeActAgent-Mistral-7b-v0.1 (recommended, model link ): using Mistral-7b-v0.1 as the base model with 32k context window.
• CodeActAgent-Llama-7b ( model link ): using Llama-2-7b as the base model with 4k context window.

Evaluation results for CodeActAgent. ID and OD stand for in-domain and out-of-domain evaluation correspondingly. Overall averaged performance normalizes the MT-Bench score to be consistent with other tasks and excludes in-domain tasks for fair comparison.

Please check out our paper and code for more details about data collection, model training, and evaluation.

📚 Citation

@misc{wang2024executable,
      title={Executable Code Actions Elicit Better LLM Agents}, 
      author={Xingyao Wang and Yangyi Chen and Lifan Yuan and Yizhe Zhang and Yunzhu Li and Hao Peng and Heng Ji},
      year={2024},
      eprint={2402.01030},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}