RL-Forgetting-Experiments-3/qwen2.5-3b-code-sft-replay-uniform-lam1-step102

q25sftrpuniformlam1

Inference-ready final coding-SFT model for q25_sft_rp_uniform_lam1 at optimizer step 102. Training uses qwen3b_code_sft_data_s300, order ordered, replay strategy uniform, and replay lambda 1.0.

See delivery_manifest.json for immutable source lineage and file checksums.