Hugging Face's logo

kejian
/
gpt2-tulu2-DPO

Text Generation
Transformers
Safetensors
gpt2
text-generation-inference
Inference Endpoints
Model card Files Community
kejian commited on
Commit
b5eb36d
•
1 Parent(s): ad664bc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -1,2 +1 @@
1
- gpt-2 small (124M) on tulu2-sft mixture
2
- Then DPO 40k on UltraFeedback
 
1
+ gpt-2 small (124M) on tulu2-sft mixture +DPO 40k on UltraFeedback