xz56 commited on
Commit
38bbf30
1 Parent(s): 37030d3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -0
README.md CHANGED
@@ -1,3 +1,15 @@
1
  ---
2
  license: apache-2.0
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ datasets:
4
+ - Intel/orca_dpo_pairs
5
  ---
6
+ # Model Summary
7
+ Neuralphi-2 is an experiment in DPO finetuning. It was made following Max Labonne's excellent [article](https://towardsdatascience.com/fine-tune-a-mistral-7b-model-with-direct-preference-optimization-708042745aac) about fine-tuning mistral-7b.
8
+ Neuralphi-2 is [phi-2-sft](https://huggingface.co/lxuechen/phi-2-sft) finetuned using DPO with [Intel/orca_dpo_pairs](https://huggingface.co/datasets/Intel/orca_dpo_pairs).
9
+ # Prompt Format
10
+ ```
11
+ """### Human: {instruction}
12
+
13
+ ### Assistant:"""
14
+ ```
15
+