Files
qwen3-dpo-grpo/README.md
ModelHub XC 42f34b0d10 初始化项目,由ModelHub XC社区提供模型
Model: Phantomcloak19/qwen3-dpo-grpo
Source: Original Platform
2026-08-15 16:11:23 +08:00

9 lines
141 B
Markdown

---
base_model: Qwen/Qwen3-4B
library_name: transformers
tags:
- horus-llm
- dpo-grpo
---
# qwen3-4b — DPO-GRPO (QLoRA, K=4, ctx=6168)