Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,7 @@ pipeline_tag: text2text-generation
|
|
| 10 |
tags:
|
| 11 |
- text-generation-inference
|
| 12 |
---
|
| 13 |
-
# HK-O1aw(v0)
|
| 14 |
HK-O1aw is a legal assistant with <u>O1-style</u> complex reasoning capabilities, trained using the [Align-Anything](https://github.com/PKU-Alignment/align-anything) framework on the [O1aw-Dataset](https://github.com/HKAIR-Lab/HK-O1aw), based on LLaMA-3.1-8B (pre-trained version).
|
| 15 |
|
| 16 |
HK-O1aw aims to enhance large language models' reasoning capabilities and complex problem-solving abilities in the legal domain (specifically in Hong Kong). More importantly, HK-O1aw has open-sourced all training data, code, and prompts used for synthetic data generation, providing greater convenience for the community and researchers.
|
|
|
|
| 10 |
tags:
|
| 11 |
- text-generation-inference
|
| 12 |
---
|
| 13 |
+
# HK-O1aw (v0)
|
| 14 |
HK-O1aw is a legal assistant with <u>O1-style</u> complex reasoning capabilities, trained using the [Align-Anything](https://github.com/PKU-Alignment/align-anything) framework on the [O1aw-Dataset](https://github.com/HKAIR-Lab/HK-O1aw), based on LLaMA-3.1-8B (pre-trained version).
|
| 15 |
|
| 16 |
HK-O1aw aims to enhance large language models' reasoning capabilities and complex problem-solving abilities in the legal domain (specifically in Hong Kong). More importantly, HK-O1aw has open-sourced all training data, code, and prompts used for synthetic data generation, providing greater convenience for the community and researchers.
|