Instructions to use infly/INFLogic-Qwen2.5-32B-RL-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use infly/INFLogic-Qwen2.5-32B-RL-Preview with Transformers:

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

pipe = pipeline("text-generation", model="infly/INFLogic-Qwen2.5-32B-RL-Preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("infly/INFLogic-Qwen2.5-32B-RL-Preview")
model = AutoModelForCausalLM.from_pretrained("infly/INFLogic-Qwen2.5-32B-RL-Preview")
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

vLLM

How to use infly/INFLogic-Qwen2.5-32B-RL-Preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "infly/INFLogic-Qwen2.5-32B-RL-Preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "infly/INFLogic-Qwen2.5-32B-RL-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/infly/INFLogic-Qwen2.5-32B-RL-Preview

SGLang

How to use infly/INFLogic-Qwen2.5-32B-RL-Preview 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 "infly/INFLogic-Qwen2.5-32B-RL-Preview" \
    --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": "infly/INFLogic-Qwen2.5-32B-RL-Preview",
		"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 "infly/INFLogic-Qwen2.5-32B-RL-Preview" \
        --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": "infly/INFLogic-Qwen2.5-32B-RL-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use infly/INFLogic-Qwen2.5-32B-RL-Preview with Docker Model Runner:
```
docker model run hf.co/infly/INFLogic-Qwen2.5-32B-RL-Preview
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

INFLogic-Qwen2.5-32B-RL-Preview

Model Overview

INFLogic-Qwen2.5-32B-RL-Preview enhances the reasoning capabilities of DeepSeek-R1-Distill-Qwen-32B through fine-tuning on our proprietary logical reasoning dataset using reinforcement learning with verifiable rewards (RLVR).
As of March 27th, 2025, this model achieves state-of-the-art performance among open-source LLMs on ZebraLogicBench, demonstrating enhanced logical reasoning abilities.

Evaluation Results

Model	MATH-500	ZebraLogic	GPQA
INFLogic-Qwen2.5-32B-RL-Preview	95.6	85.1	65.7
DeepSeek-R1-Distill-Qwen-32B	94.3	68.7	62.1
DeepSeek-R1	96.2	77.2	78.9
OpenAI o1	96.4	87.9	85.2

Detailed result

Metric	Value
Puzzle Acc	0.851
Small Puzzle Acc	0.982
Medium Puzzle Acc	0.969
Large Puzzle Acc	0.848
XL Puzzle Acc	0.480
Total Puzzles	1000
N_Mode	single
N_Size	1
Reason Lens	559.9

We report pass@1 scores using vLLM 0.5.3 (temperature=0.6, top_p=0.95). For MATH-500 and GPQA, we used Open R1's evaluation scripts. Other models' results come from their original reports.

Contributors

Supervisors

Wei Chu • Yuan Qi

Logic Team

Cheng Peng • Shuyao Xu • Weidi Xu

Acknowledgments

We thank Chao Qu, Haozhe Wang, Jiaran Hao, and Liuyihan Song for their valuable discussions and support.

Citation

If you find our model useful, please consider citing:

@misc{INFLogic_RL_Preview,
  author       = {Peng, Cheng and Xu, Shuyao and Xu, Weidi and Chu, Wei and Qi, Yuan},
  title        = {INFLogic-Qwen2.5-32B-RL-Preview},
  year         = {2025},
  month        = {March},
  howpublished = {Hugging Face},
  url          = {https://huggingface.co/infly/INFLogic-Qwen2.5-32B-RL-Preview},
}

Downloads last month: 15

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for infly/INFLogic-Qwen2.5-32B-RL-Preview

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

Finetuned

(85)

this model

Quantizations

1 model

infly
/

INFLogic-Qwen2.5-32B-RL-Preview