---
library_name: transformers
base_model: Qwen/Qwen2.5-3B
private: false
tags:
- supervised-fine-tuning
- code
- mbpp
---

# q25_sft_rp_uniform_lam1

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.