Instructions to use code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt")
model = AutoModelForCausalLM.from_pretrained("code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt

SGLang

How to use code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt with Docker Model Runner:
```
docker model run hf.co/code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt
```

Qwen3-8B-Critic-SFT-Detailed-Prompt

An 8B critic from Steer, Don't Solve: Training Small Critic Models for Large Code Agents, trained on teacher critiques collected with the detailed prompt instead of the high-level one. It is the comparison arm of the prompt ablation (Table 4). The critic trained on high-level critiques is Qwen3-8B-Critic-SFT.

The two prompts differ in what the teacher is allowed to say. The high-level prompt asks for error detection plus short guidance and forbids full solutions. The detailed prompt lets the teacher propose concrete code-level fixes, so its critiques are longer and often contain code. The paper shows that agents copy this code (Table 5), and that a small critic trained on detailed critiques ends up weaker than one trained on high-level critiques.

All released models and datasets are listed on the organization page. Code and configs are in the critic-training repository.

Where it appears in the paper

Paper location	Row label
Table 4, prompt ablation	`+ SFT (Detailed-Prompt)`

Original run name: qwen3-8b-full-sft-prm-r2egym-swebench-k5-opus-distill-32k-lr5e6-multiturn. In the repository the detailed prompt is the prm_issue_res config family and the high-level prompt is prm_issue_res_instructions.

Training data

code-critic-model/critic-sft-cwm-only-detailed-prompt, 3,135 examples.

Tasks: 500 R2E-Gym instances from matplotlib, moto, and sympy, disjoint from SWE-bench Verified.
Agent that produced the trajectories: CWM-32B, 500 trajectories.
Teacher: Claude Opus 4.6, queried every 5 agent steps with the detailed prompt.

The same 500 tasks and agent as critic-sft-cwm-only; only the teacher prompt differs. Fewer examples survive the 32K token limit because detailed critiques are longer.

Training setup

Identical to Qwen3-8B-Critic-SFT apart from the data. Full-parameter SFT with LLaMA-Factory, config finetuning/qwen3_8b_critic_full_sft_l40s_train_multiturn_resumable.yaml.

Setting	Value
Base model	Qwen/Qwen3-8B
Chat template	`qwen3_nothink`
Sequence length	32,768 tokens
Loss	final critique turn only (`mask_history: true`)
Hardware	8 x L40S, effective batch 8
Optimizer	AdamW, lr 5e-6, cosine, warmup ratio 0.1
Epochs	3
Precision	bf16

Results

Resolve rate on SWE-bench Verified, from Table 4 of the paper. Both critics were run with the same high-level, step-aware inference prompt; only the training critiques differ.

Coding agent	No critic	+ this critic (detailed training critiques)	+ Qwen3-8B-Critic-SFT (high-level training critiques)
Qwen3-Next-80B-A3B	20.0	24.6	25.2
Qwen3-32B	8.8	12.6	13.8

Note that the high-level critic was trained on the larger CWM plus Qwen3-Next corpus, so this comparison also reflects the corpus difference.

How to use

Same serving and launch procedure as Qwen3-8B-Critic-SFT: serve with vLLM in bf16 and pass the served name to scripts/run_critic_max150.sh with --prm. The served name must have an entry in mini-swe-agent/configs/litellm_model_registry.json; add one for this model if you use a new name.

Citation

@misc{gandhi2026steerdontsolvetraining,
  title={Steer, Don't Solve: Training Small Critic Models for Large Code Agents},
  author={Shubham Gandhi and Yiqing Xie and Atharva Naik and Ruichen Zhu and Carolyn Rose},
  year={2026},
  eprint={2606.21811},
  archivePrefix={arXiv},
  primaryClass={cs.SE},
  url={https://arxiv.org/abs/2606.21811}
}