CoolFace
Modelpublic

RegularizedSelfPlay/sppo_reversekl-0.05-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter3

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes6downloads
3 commits on main
4c79ae92y ago

Upload tokenizer

angelahzyuan
542297e2y ago

Upload LlamaForCausalLM

angelahzyuan
2816ec12y ago

initial commit

angelahzyuan