RL-Forgetting-Experiments-3
/

code-sft-20261027-llama3b-code-ordered

Model card Files Files and versions

code-sft-20261027-llama3b-code-ordered / runs /checkpoints /step_52 /model /generation_config.json

Commit History

Oct 27 13 days ago

08:23
Publish llama3b_code_ordered_lr1e-5_bs256_seed42/checkpoints/step_52 model files

smilani

Verified signature
1e0a8bd