Metadata-Version: 2.4
Name: collabllm
Version: 0.0.5
Summary: (Oral @ ICML 2025) CollabLLM: From Passive Responders to Active Collaborators
Author-email: Shirley Wu <shirwu@stanford.edu>
License-Expression: MIT
Project-URL: Homepage, https://github.com/Wuyxin/collabllm
Project-URL: Issues, https://github.com/Wuyxin/collabllm/issues
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: accelerate
Requires-Dist: bitsandbytes
Requires-Dist: datasets
Requires-Dist: huggingface-hub
Requires-Dist: litellm
Requires-Dist: nltk
Requires-Dist: numpy
Requires-Dist: openai
Requires-Dist: pandas
Requires-Dist: peft
Requires-Dist: python-dotenv
Requires-Dist: rich
Requires-Dist: scipy
Requires-Dist: tiktoken
Requires-Dist: tokenizers
Requires-Dist: torch
Requires-Dist: tqdm
Requires-Dist: trl==0.18.1
Requires-Dist: transformers
Requires-Dist: vllm
Requires-Dist: wandb
Dynamic: license-file

# CollabLLM: From Passive Responders to Active Collaborators (ICML 2025 Oral)

[Paper](https://cs.stanford.edu/~shirwu/files/collabllm_v1.pdf)

# Installation

```bash
conda create -n collabllm python=3.10
pip install collabllm
```
You can further install additional packages for customized metric, such as `bigcodebench`. 

# Quick Start

`notebook_tutorials/`

`scripts/`

# Citation
If you use this code in your research, please cite the following paper:

```bibtex
@inproceedings{
    collabllm,
    title={CollabLLM: From Passive Responders to Active Collaborators},
    author={Shirley Wu and Michel Galley and 
            Baolin Peng and Hao Cheng and 
            Gavin Li and Yao Dou and Weixin Cai and 
            James Zou and Jure Leskovec and Jianfeng Gao
            },
    booktitle={ICML},
    year={2025}
}
```
