RL-Forgetting-Experiments-3
/

code-sft-20261027-llama3b-code-shuffled

Model card Files Files and versions

code-sft-20261027-llama3b-code-shuffled / runs /checkpoints /step_39 /model /tokenizer.json

Commit History

Oct 27 13 days ago

12:15
Publish llama3b_code_shuffled_lr1e-5_bs256_seed42/checkpoints/step_39 model files

smilani

Verified signature
afc3a6c