DaYin commited on
Commit
808a11d
β€’
1 Parent(s): 5665bf5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +50 -0
README.md CHANGED
@@ -1,3 +1,53 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ datasets:
4
+ - ai2lumos/lumos_web_agent_plan_iterative
5
+ language:
6
+ - en
7
+ tags:
8
+ - language-agent
9
+ - web-agent
10
+ - reasoning
11
+ - planning
12
  ---
13
+
14
+ # πŸͺ„ Lumos: Language Agents with Unified Formats, Modular Design, and Open-Source LLMs
15
+ <p align="center">
16
+ 🌐<a href="https://allenai.github.io/lumos">[Website]</a> &nbsp;
17
+ πŸ“<a href="">[Paper]</a> &nbsp;
18
+ πŸ€—<a href="https://huggingface.co/datasets?sort=trending&search=ai2lumos">[Data]</a> &nbsp;
19
+ πŸ€—<a href="https://huggingface.co/models?sort=trending&search=ai2lumos">[Model]</a> &nbsp;
20
+ </p>
21
+
22
+ We introduce πŸͺ„**Lumos**, Language Agents with **Unified** Formats, **Modular** Design, and **Open-Source** LLMs. **Lumos** unifies a suite of complex interactive tasks and achieves competitive performance with GPT-4/3.5-based and larger open-source agents.
23
+
24
+ **Lumos** has following features:
25
+ * 🧩 **Modular Architecture**:
26
+ - **Lumos** consists of planning, grounding, and execution modules built based on LLAMA-2-7B.
27
+ * 🌍 **Diverse Training Data**:
28
+ - **Lumos** is trained with ~40K high-quality annotations from ground-truth reasoning steps in existing benchmarks with GPT-4.
29
+ * πŸš€ **Competitive Performance**:
30
+ - πŸš€ **Lumos** outperforms **GPT-4/3.5-based** agents on complex QA and web agent tasks, and **larger open agents** on maths tasks.
31
+ - πŸš€ **Lumos** performs better than open agent baseline formulations including **chain-of-thoughts** and **unmodularized** training.
32
+ - πŸš€ **Lumos** surpasses larger open LLM agents and domain-specific agents on an unseen task, WebShop.
33
+
34
+ ## Model Overview
35
+ `lumos_web_agent_plan_iterative` is a **planning** module checkpoint finetuned on **web agent** task in **Lumos-Iterative (Lumos-I)** formulation.
36
+
37
+ The training annotation is shown below:
38
+
39
+ | Training Data | Number |
40
+ |---|---|
41
+ |[`lumos_web_agent_plan_iterative`](https://huggingface.co/datasets/ai2lumos/lumos_web_agent_plan_iterative)|1009|
42
+
43
+
44
+ ## Citation
45
+
46
+ If you find this work is relevant with your research, please feel free to cite our work!
47
+ ```
48
+ @article{yin2023lumos,
49
+ title={Lumos: Towards Language Agents that are Unified, Modular, and Open Source},
50
+ author={Yin, Da and Brahman, Faeze and Ravichander, Abhilasha and Chandu, Khyathi and Chang, Kai-Wei and Choi, Yejin and Lin, Bill Yuchen},
51
+ year={2023}
52
+ }
53
+ ```