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_65 /model /config.json

Commit History

Oct 27 13 days ago

09:18
Publish llama3b_code_ordered_lr1e-5_bs256_seed42/checkpoints/step_65 model files

smilani

Verified signature
893ff5a