kejian
/

gpt2-tulu2-DPO

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

gpt2-tulu2-DPO / README.md

kejian's picture

Update README.md

ad664bc verified 8 months ago

|

69 Bytes

gpt-2 small (124M) on tulu2-sft mixture Then DPO 40k on UltraFeedback