QREF — Deep-Research Agent (Qwen3-8B SFT + RL)
Final checkpoints of our deep-research / web-agent pipeline, built on top of Qwen3-8B.
| Subfolder | Stage | Training step |
|---|---|---|
SFT/ |
Supervised Fine-Tuning | global_step = 1099 |
RL/ |
Reinforcement Learning | global_step = 166 |
Both checkpoints share the same architecture (Qwen3ForCausalLM, bfloat16) and tokenizer as the base model.
License
Apache-2.0, following the base model's license.