---
base_model: Qwen/Qwen3-4B
library_name: transformers
tags:
  - horus-llm
  - dpo
  - qwen3-4b
---

# qwen3-4b — DPO

Merged full-precision model after the **DPO** phase of the
HorusLLM sequential training pipeline (SFT → DPO → Safety-GRPO).

| Field | Value |
|---|---|
| Base model | `Qwen/Qwen3-4B` |
| Phase | DPO |
| Short name | qwen3-4b |
| Generated | 2026-07-01 19:31 UTC |