kashif HF staff commited on
Commit
0cf5c13
1 Parent(s): 375f128

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -54,7 +54,7 @@ Fine-tuning datasets for this model are based on [Stack Exchange Paired](https:/
54
  **DPO Training:** [https://huggingface.co/datasets/lvwerra/stack-exchange-paired/tree/main/data/rl](https://huggingface.co/datasets/lvwerra/stack-exchange-paired/tree/main/data/rl)
55
 
56
  ### Training Procedure
57
- The model was first fine-tuned on the Stack Exchange question and answer pairs and then fine-tuned via the DPO training procedure using a Stack Exchange Reward Model.
58
  It is trained to respond to prompts with the following template:
59
 
60
  ```
 
54
  **DPO Training:** [https://huggingface.co/datasets/lvwerra/stack-exchange-paired/tree/main/data/rl](https://huggingface.co/datasets/lvwerra/stack-exchange-paired/tree/main/data/rl)
55
 
56
  ### Training Procedure
57
+ The model was first fine-tuned on the Stack Exchange question and answer pairs and then fine-tuned via the DPO training procedure using the SFT model as the reference model.
58
  It is trained to respond to prompts with the following template:
59
 
60
  ```