RichardErkhov/xingyaoww_-_CodeActAgent-Llama-2-7b-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

CodeActAgent-Llama-2-7b - GGUF

• Model creator: https://huggingface.co/xingyaoww/
• Original model: https://huggingface.co/xingyaoww/CodeActAgent-Llama-2-7b/

Name	Quant method	Size
CodeActAgent-Llama-2-7b.Q2_K.gguf	Q2_K	2.36GB
CodeActAgent-Llama-2-7b.IQ3_XS.gguf	IQ3_XS	2.6GB
CodeActAgent-Llama-2-7b.IQ3_S.gguf	IQ3_S	2.75GB
CodeActAgent-Llama-2-7b.Q3_K_S.gguf	Q3_K_S	2.75GB
CodeActAgent-Llama-2-7b.IQ3_M.gguf	IQ3_M	2.9GB
CodeActAgent-Llama-2-7b.Q3_K.gguf	Q3_K	3.07GB
CodeActAgent-Llama-2-7b.Q3_K_M.gguf	Q3_K_M	3.07GB
CodeActAgent-Llama-2-7b.Q3_K_L.gguf	Q3_K_L	3.35GB
CodeActAgent-Llama-2-7b.IQ4_XS.gguf	IQ4_XS	3.4GB
CodeActAgent-Llama-2-7b.Q4_0.gguf	Q4_0	3.56GB
CodeActAgent-Llama-2-7b.IQ4_NL.gguf	IQ4_NL	3.58GB
CodeActAgent-Llama-2-7b.Q4_K_S.gguf	Q4_K_S	3.59GB
CodeActAgent-Llama-2-7b.Q4_K.gguf	Q4_K	3.8GB
CodeActAgent-Llama-2-7b.Q4_K_M.gguf	Q4_K_M	3.8GB
CodeActAgent-Llama-2-7b.Q4_1.gguf	Q4_1	3.95GB
CodeActAgent-Llama-2-7b.Q5_0.gguf	Q5_0	4.33GB
CodeActAgent-Llama-2-7b.Q5_K_S.gguf	Q5_K_S	4.33GB
CodeActAgent-Llama-2-7b.Q5_K.gguf	Q5_K	4.45GB
CodeActAgent-Llama-2-7b.Q5_K_M.gguf	Q5_K_M	4.45GB
CodeActAgent-Llama-2-7b.Q5_1.gguf	Q5_1	4.72GB
CodeActAgent-Llama-2-7b.Q6_K.gguf	Q6_K	5.15GB
CodeActAgent-Llama-2-7b.Q8_0.gguf	Q8_0	6.67GB

Original model description:

license: llama2 datasets: - xingyaoww/code-act language: - en tags: - llm-agent pipeline_tag: text-generation

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’ actions 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 M³ToolEval 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 M³ToolEval.

📁 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}
}