README.md

---
license: apache-2.0
library_name: transformers
base_model: Qwen/Qwen3.5-9B
tags:
  - harness-r1
  - agent
  - reinforcement-learning
---

# Harness-R1

Harness-engineer checkpoints from the paper main table.

| Subfolder | Paper row |
|---|---|
| [`harness-r1`](./harness-r1) | Harness-R1 |
| [`agent-sft-harness-r1`](./agent-sft-harness-r1) | Agent SFT + Harness-R1 |

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "ShaoShuai0605/Harness-R1"
subfolder = "harness-r1"  # or agent-sft-harness-r1
tok = AutoTokenizer.from_pretrained(repo, subfolder=subfolder, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(repo, subfolder=subfolder, trust_remote_code=True)
```