Update README.md
Browse files
README.md
CHANGED
|
@@ -1,19 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
datasets:
|
| 4 |
-
- UI-Simulator/UI-Simulator_web_data
|
| 5 |
-
language:
|
| 6 |
-
- en
|
| 7 |
-
base_model:
|
| 8 |
-
- meta-llama/Meta-Llama-3-8B-Instruct
|
| 9 |
-
pipeline_tag: text-generation
|
| 10 |
-
tags:
|
| 11 |
-
- agent
|
| 12 |
-
---
|
| 13 |
# Model Card for Model ID
|
| 14 |
|
| 15 |
-
This is the UI-Simulator model that is trained on
|
| 16 |
|
| 17 |
## Uses
|
| 18 |
|
| 19 |
-
We provide a script for loading the model and run WebArena evaluation [here](https://github.com/WadeYin9712/UI-Simulator/blob/main/webarena/run.py)
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- UI-Simulator/UI-Simulator_web_data
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
base_model:
|
| 8 |
+
- meta-llama/Meta-Llama-3-8B-Instruct
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
+
tags:
|
| 11 |
+
- agent
|
| 12 |
+
- web-agent
|
| 13 |
+
- world-model
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
# π UI-Simulator: LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training
|
| 17 |
+
|
| 18 |
+
[](LICENSE)
|
| 19 |
+
[]()
|
| 20 |
+
[]()
|
| 21 |
+
[]()
|
| 22 |
+
|
| 23 |
+
π **Paper link**: [Link]()
|
| 24 |
+
|
| 25 |
+
π **Website**: https://ui-simulator.notion.site/llms-as-scalable-digital-world-simulator
|
| 26 |
+
|
| 27 |
+
π **Github:** https://github.com/WadeYin9712/UI-Simulator
|
| 28 |
+
|
| 29 |
+
π§ **Contact:** [da.yin9712@gmail.com](mailto:da.yin9712@gmail.com), [w10y20ming@gmail.com](mailto:w10y20ming@gmail.com)
|
| 30 |
+
|
| 31 |
---
|
| 32 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
# Model Card for Model ID
|
| 34 |
|
| 35 |
+
This is the UI-Simulator model that is trained on retrieval-free web UI-Simulator. It is trained to solve WebArena tasks.
|
| 36 |
|
| 37 |
## Uses
|
| 38 |
|
| 39 |
+
We provide a script for loading the model and run WebArena evaluation [here](https://github.com/WadeYin9712/UI-Simulator/blob/main/webarena/run.py).
|