Instructions to use opencsg/OpenCSG-R1-Qwen2.5-Code-3B-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use opencsg/OpenCSG-R1-Qwen2.5-Code-3B-V1 with Transformers:

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

pipe = pipeline("text-generation", model="opencsg/OpenCSG-R1-Qwen2.5-Code-3B-V1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("opencsg/OpenCSG-R1-Qwen2.5-Code-3B-V1")
model = AutoModelForCausalLM.from_pretrained("opencsg/OpenCSG-R1-Qwen2.5-Code-3B-V1")
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 opencsg/OpenCSG-R1-Qwen2.5-Code-3B-V1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "opencsg/OpenCSG-R1-Qwen2.5-Code-3B-V1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "opencsg/OpenCSG-R1-Qwen2.5-Code-3B-V1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/opencsg/OpenCSG-R1-Qwen2.5-Code-3B-V1

SGLang

How to use opencsg/OpenCSG-R1-Qwen2.5-Code-3B-V1 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 "opencsg/OpenCSG-R1-Qwen2.5-Code-3B-V1" \
    --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": "opencsg/OpenCSG-R1-Qwen2.5-Code-3B-V1",
		"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 "opencsg/OpenCSG-R1-Qwen2.5-Code-3B-V1" \
        --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": "opencsg/OpenCSG-R1-Qwen2.5-Code-3B-V1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use opencsg/OpenCSG-R1-Qwen2.5-Code-3B-V1 with Docker Model Runner:
```
docker model run hf.co/opencsg/OpenCSG-R1-Qwen2.5-Code-3B-V1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for OpenCSG-R1-Qwen2.5-Code-3B-V1

This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-3B-Instruct] (https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct) on the [open-r1/OpenThoughts-114k-Code_decontaminated] datasets. It has been trained using TRL.

Quick start

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
import pandas as pd

model_name = "/data/project/pj/r1/opencsg-r1/open-r1/train/Qwen2.5-3B-Open-R1-Code-GRPO/checkpoint-150"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=False)
df = pd.read_parquet('/data/project/pj/r1/opencsg-r1/OpenThoughts-114k-Code_decontaminated/train-00000-of-00006.parquet')
data = df['problem'][0]
messages = [
    {
        "role": "user",
         "content": f"Please help me solve the problem: {data}.Output the thinking process within the <think> </think> tags,and then return the final result within the <answer> </answer> tags.",
    },
    {
        "role": "assistant",
        "content": "Let's solve the problem step by step.\n<think>",
    },
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    continue_final_message=True,
    # add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=1024,
    temperature=0.6
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

This model was trained with GRPO, a method introduced in DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Framework versions

TRL: 0.15.2
Transformers: 4.49.0
Pytorch: 2.5.1
Datasets: 3.3.2
Tokenizers: 0.21.0

Citations

Cite GRPO as:

@article{zhihong2024deepseekmath,
    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
    year         = 2024,
    eprint       = {arXiv:2402.03300},
}

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}