lambdax commited on
Commit
7536176
1 Parent(s): bb63910

Add citation

Browse files
Files changed (1) hide show
  1. README.md +15 -2
README.md CHANGED
@@ -5,9 +5,8 @@ datasets:
5
 
6
  ## AgentLM-7B
7
 
8
-
9
  <p align="center">
10
- 🤗 <a href="https://huggingface.co/datasets/THUDM/AgentInstruct" target="_blank">[Dataset] </a> • 💻 <a href="https://github.com/THUDM/AgentTuning" target="_blank">[Github Repo]</a> • 📌 <a href="https://THUDM.github.io/AgentTuning/" target="_blank">[Project Page]</a> • 📃 <a href="https://arxiv.org/abs/TODO" target="_blank">[Paper]</a>
11
  </p>
12
 
13
  **AgentTuning** represents the very first attempt to instruction-tune LLMs using interaction trajectories across multiple agent tasks. Evaluation results indicate that AgentTuning enables the agent capabilities of LLMs with robust generalization on unseen agent tasks while remaining good on general language abilities. We have open-sourced the AgentInstruct dataset and AgentLM.
@@ -30,3 +29,17 @@ You are a helpful, respectful and honest assistant.
30
  |AgentLM-13B| [🤗Huggingface Repo](https://huggingface.co/THUDM/agentlm-13b) |
31
  |AgentLM-70B| [🤗Huggingface Repo](https://huggingface.co/THUDM/agentlm-70b) |
32
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
 
6
  ## AgentLM-7B
7
 
 
8
  <p align="center">
9
+ 🤗 <a href="https://huggingface.co/datasets/THUDM/AgentInstruct" target="_blank">[Dataset] </a> • 💻 <a href="https://github.com/THUDM/AgentTuning" target="_blank">[Github Repo]</a> • 📌 <a href="https://THUDM.github.io/AgentTuning/" target="_blank">[Project Page]</a> • 📃 <a href="https://arxiv.org/abs/2310.12823" target="_blank">[Paper]</a>
10
  </p>
11
 
12
  **AgentTuning** represents the very first attempt to instruction-tune LLMs using interaction trajectories across multiple agent tasks. Evaluation results indicate that AgentTuning enables the agent capabilities of LLMs with robust generalization on unseen agent tasks while remaining good on general language abilities. We have open-sourced the AgentInstruct dataset and AgentLM.
 
29
  |AgentLM-13B| [🤗Huggingface Repo](https://huggingface.co/THUDM/agentlm-13b) |
30
  |AgentLM-70B| [🤗Huggingface Repo](https://huggingface.co/THUDM/agentlm-70b) |
31
 
32
+ ## Citation
33
+
34
+ If you find our work useful, please consider citing AgentTuning:
35
+
36
+ ```
37
+ @misc{zeng2023agenttuning,
38
+ title={AgentTuning: Enabling Generalized Agent Abilities for LLMs},
39
+ author={Aohan Zeng and Mingdao Liu and Rui Lu and Bowen Wang and Xiao Liu and Yuxiao Dong and Jie Tang},
40
+ year={2023},
41
+ eprint={2310.12823},
42
+ archivePrefix={arXiv},
43
+ primaryClass={cs.CL}
44
+ }
45
+ ```