Safetensors
xzuyn commited on
Commit
0073e27
1 Parent(s): 3eeaba3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -2
README.md CHANGED
@@ -3,6 +3,9 @@ datasets:
3
  - PJMixers/antiven0m_catboros-3.2-dpo-PreferenceShareGPT
4
  - antiven0m/catboros-3.2-dpo
5
  ---
6
- ![Chosen/Rejected Reward Graph](https://huggingface.co/PJMixers/LLaMa-3-Instruct-Catboros-3.2-ORPO-8B-QDoRA/resolve/main/chosen_rejected_reward_graph.png)
7
 
8
- Trained on [antiven0m/catboros-3.2-dpo](https://huggingface.co/datasets/antiven0m/catboros-3.2-dpo).
 
 
 
 
3
  - PJMixers/antiven0m_catboros-3.2-dpo-PreferenceShareGPT
4
  - antiven0m/catboros-3.2-dpo
5
  ---
6
+ Trained on [antiven0m/catboros-3.2-dpo](https://huggingface.co/datasets/antiven0m/catboros-3.2-dpo).
7
 
8
+ ![train/rewards](https://huggingface.co/PJMixers/LLaMa-3-Instruct-Catboros-3.2-ORPO-8B-QDoRA/resolve/main/images/rewards.png)
9
+ ![train/logits](https://huggingface.co/PJMixers/LLaMa-3-Instruct-Catboros-3.2-ORPO-8B-QDoRA/resolve/main/images/logits.png)
10
+ ![train/logps](https://huggingface.co/PJMixers/LLaMa-3-Instruct-Catboros-3.2-ORPO-8B-QDoRA/resolve/main/images/logps.png)
11
+ ![train](https://huggingface.co/PJMixers/LLaMa-3-Instruct-Catboros-3.2-ORPO-8B-QDoRA/resolve/main/images/train.png)