BlouseJury commited on
Commit
3fde205
1 Parent(s): 8643c31

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -18
README.md CHANGED
@@ -4,13 +4,10 @@ base_model: BlouseJury/Mistral-7B-Discord-0.1
4
  tags:
5
  - generated_from_trainer
6
  model-index:
7
- - name: out
8
  results: []
9
  ---
10
 
11
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
- should probably proofread and complete it, then remove this comment. -->
13
-
14
  [<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)
15
  <details><summary>See axolotl config</summary>
16
 
@@ -89,24 +86,12 @@ special_tokens:
89
 
90
  </details><br>
91
 
92
- # out
93
 
94
- This model is a fine-tuned version of [BlouseJury/Mistral-7B-Discord-0.1](https://huggingface.co/BlouseJury/Mistral-7B-Discord-0.1) on the None dataset.
95
  It achieves the following results on the evaluation set:
96
  - Loss: 0.7923
97
 
98
- ## Model description
99
-
100
- More information needed
101
-
102
- ## Intended uses & limitations
103
-
104
- More information needed
105
-
106
- ## Training and evaluation data
107
-
108
- More information needed
109
-
110
  ## Training procedure
111
 
112
  ### Training hyperparameters
 
4
  tags:
5
  - generated_from_trainer
6
  model-index:
7
+ - name: Mistral-7B-Discord-0.1-DPO
8
  results: []
9
  ---
10
 
 
 
 
11
  [<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)
12
  <details><summary>See axolotl config</summary>
13
 
 
86
 
87
  </details><br>
88
 
89
+ # BlouseJury/Mistral-7B-Discord-0.1-DPO
90
 
91
+ This model is a fine-tuned version of [BlouseJury/Mistral-7B-Discord-0.1](https://huggingface.co/BlouseJury/Mistral-7B-Discord-0.1) on the Intel/orca_dpo_pairs dataset.
92
  It achieves the following results on the evaluation set:
93
  - Loss: 0.7923
94
 
 
 
 
 
 
 
 
 
 
 
 
 
95
  ## Training procedure
96
 
97
  ### Training hyperparameters