HenryJJ commited on
Commit
3b71102
1 Parent(s): 5a78925

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -8,6 +8,8 @@ datasets:
8
  Dpo trained from cognitivecomputations/dolphin-2.6-mistral-7b, used Intel/orca_dpo_pairs for the dataset.
9
  Trained for 1200 steps. Trained with 1024 context window.
10
 
 
 
11
  # Model Details
12
  * **Trained by**: trained by HenryJJ.
13
  * **Model type:** **dolphin-2.6-mistral-7b-dpo-orca** is an auto-regressive language model based on the Llama 2 transformer architecture.
 
8
  Dpo trained from cognitivecomputations/dolphin-2.6-mistral-7b, used Intel/orca_dpo_pairs for the dataset.
9
  Trained for 1200 steps. Trained with 1024 context window.
10
 
11
+ Training code: https://github.com/hengjiUSTC/learn-llm/blob/main/dpo_demo.ipynb
12
+
13
  # Model Details
14
  * **Trained by**: trained by HenryJJ.
15
  * **Model type:** **dolphin-2.6-mistral-7b-dpo-orca** is an auto-regressive language model based on the Llama 2 transformer architecture.