Dipto084
/

llama31-8b-gdpo-v7-step35

Model card Files Files and versions

llama31-8b-gdpo-v7-step35 / tokenizer.json

Dipto084's picture

Initial: Llama-3.1-8B GDPO v7 step 35 (merged) — best safety/helpfulness balance per PHTest+val_20

ff5a1bb verified 27 days ago

history contribute delete

9.09 MB

File too large to display, you can check the raw version instead.