RL-Forgettting-Exp4
/

code-sft-rerun-20261102-qwen3b-code-ordered

Model card Files Files and versions

code-sft-rerun-20261102-qwen3b-code-ordered

12.4 GB

Ctrl+K

Ctrl+K

1 contributor

History: 4 commits

smilani's picture

Publish qwen3b_code_ordered_lr1e-5_bs256_seed42_s300/final model files

a0cd5ef verified 5 days ago

runs
Publish qwen3b_code_ordered_lr1e-5_bs256_seed42_s300/final model files 5 days ago
.gitattributes

1.58 kB
Publish qwen3b_code_ordered_lr1e-5_bs256_seed42_s300/final model files 5 days ago
LICENSE

7.39 kB
Preserve base model license and modification attribution 5 days ago
NOTICE

282 Bytes
Preserve base model license and modification attribution 5 days ago
README.md

1.49 kB
Describe incremental filtered SFT delivery 5 days ago