Instructions to use gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B with Transformers:

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

pipe = pipeline("text-generation", model="gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B")
model = AutoModelForCausalLM.from_pretrained("gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B

SGLang

How to use gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B 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 "gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B" \
    --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": "gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B",
		"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 "gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B" \
        --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": "gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B with Docker Model Runner:
```
docker model run hf.co/gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B
```

Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B distilled from Skywork/Skywork-OR1-Math-7B with Ask to Distill.

Ask to Distill trains a question generator with RL so that the questions it writes expose bounded, learnable token-level disagreement between a teacher and a student on the student's own solutions (the same signal on-policy distillation learns from). A question bank is then sampled from the generator, filtered and deduplicated, and the student is trained with on-policy distillation (OPD) on it. No real training questions and no reference answers are used.

Training


Student	deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
Teacher	Skywork/Skywork-OR1-Math-7B
Question bank	gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B
OPD objective	per-token reverse KL on the student's top-16 tokens, weighted by renormalised student probabilities; no outcome reward
OPD recipe	lr 1e-6 (constant), AdamW, rollout temperature 1.0, fp32 master weights / bf16 compute

Results

AIME24	AIME25	AIME26	AMC23	BRUMO25	MATH500	avg6
57.5	44.8	52.5	89.2	53.3	89.9	64.54

avg@16 (MATH500: avg@4), temperature 0.7, top-p 0.95, max 31,744 new tokens. avg6 = mean of the six benchmarks.

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
repo = "gasolsun/Math_DeepSeek-R1-Distill-Qwen-7B_Skywork-OR1-Math-7B"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "..."}]
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(inputs, max_new_tokens=4096, do_sample=True, temperature=0.7, top_p=0.95)
print(tok.decode(out[0, inputs.shape[1]:], skip_special_tokens=True))

Evaluation prompt (user turn): Solve the following math problem step by step. The last line of your response should be of the form Answer: $Answer (without quotes) where $Answer is the answer to the problem.\n\n{problem}\n\nRemember to put your answer on its own line after "Answer:". Please reason step by step, and put your final answer within \\boxed{}.