seungduk commited on
Commit
0209b0b
1 Parent(s): ba710d9

Correct the trainer used for DPO

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -7,6 +7,7 @@ model-index:
7
  - name: yanolja/EEVE-Korean-Instruct-2.8B-v1.0
8
  results: []
9
  ---
 
10
 
11
  <p align="left">
12
  <img src="https://huggingface.co/yanolja/EEVE-Korean-Instruct-2.8B-v1.0/resolve/main/eeve_logo.webp" width="50%"/>
@@ -28,7 +29,7 @@ If you're passionate about the field of Large Language Models and wish to exchan
28
 
29
  ## About the Model
30
 
31
- This model is a fine-tuned version of [yanolja/EEVE-Korean-2.8B-v1.0](https://huggingface.co/yanolja/EEVE-Korean-2.8B-v1.0), which is a Korean vocabulary-extended version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2). Specifically, we employed Direct Preference Optimization (DPO) based on [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory).
32
 
33
  ## Prompt Template
34
  ```
 
7
  - name: yanolja/EEVE-Korean-Instruct-2.8B-v1.0
8
  results: []
9
  ---
10
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
11
 
12
  <p align="left">
13
  <img src="https://huggingface.co/yanolja/EEVE-Korean-Instruct-2.8B-v1.0/resolve/main/eeve_logo.webp" width="50%"/>
 
29
 
30
  ## About the Model
31
 
32
+ This model is a fine-tuned version of [yanolja/EEVE-Korean-2.8B-v1.0](https://huggingface.co/yanolja/EEVE-Korean-2.8B-v1.0), which is a Korean vocabulary-extended version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2). Specifically, we utilized Direct Preference Optimization (DPO) through the use of [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl).
33
 
34
  ## Prompt Template
35
  ```