Instructions to use junnyu/DeepScaleR-1.5B-Preview-Reproduce with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use junnyu/DeepScaleR-1.5B-Preview-Reproduce with Transformers:

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

pipe = pipeline("text-generation", model="junnyu/DeepScaleR-1.5B-Preview-Reproduce")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("junnyu/DeepScaleR-1.5B-Preview-Reproduce")
model = AutoModelForCausalLM.from_pretrained("junnyu/DeepScaleR-1.5B-Preview-Reproduce")
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 junnyu/DeepScaleR-1.5B-Preview-Reproduce with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "junnyu/DeepScaleR-1.5B-Preview-Reproduce"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "junnyu/DeepScaleR-1.5B-Preview-Reproduce",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/junnyu/DeepScaleR-1.5B-Preview-Reproduce

SGLang

How to use junnyu/DeepScaleR-1.5B-Preview-Reproduce 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 "junnyu/DeepScaleR-1.5B-Preview-Reproduce" \
    --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": "junnyu/DeepScaleR-1.5B-Preview-Reproduce",
		"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 "junnyu/DeepScaleR-1.5B-Preview-Reproduce" \
        --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": "junnyu/DeepScaleR-1.5B-Preview-Reproduce",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use junnyu/DeepScaleR-1.5B-Preview-Reproduce with Docker Model Runner:
```
docker model run hf.co/junnyu/DeepScaleR-1.5B-Preview-Reproduce
```

junnyu commited on Feb 26, 2025

Commit

0fd07d7

verified ·

1 Parent(s): 7974a98

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -42,20 +42,20 @@ nohup bash run_deepscaler_1.5b_24k.sh --model $MODEL_PATH > stage3-continue.log
 ```
 ## Evaluation
-We report Pass@1 accuracy averaged over 16 samples for each problem.
 | Model | AIME 2024 | MATH 500 | AMC 2023 | Minerva Math | OlympiadBench | Avg. |
 |-------|-----------|-----------|-----------|--------------|---------------|------|
 | Qwen-2.5-7B-Instruct | 13.3 | 79.8 | 50.6 | 34.6 | 40.7 | 43.8 |
 | rStar-Math-7B | 26.7 | 78.4 | 47.5 | - | 47.1 | - |
 | Eurus-2-7B-PRIME | 26.7 | 79.2 | 57.8 | 38.6 | 42.1 | 48.9 |
-| Qwen2.5-7B-SimpleRL | 26.7 | 82.4 | 62.5 | <strong>39.7</strong> | 43.3 | 50.9 |
 | DeepSeek-R1-Distill-Qwen-1.5B | 28.8 | 82.8 | 62.9 | 26.5 | 43.3 | 48.9 |
 | Still-1.5B | 32.5 | 84.4 | 66.7 | 29.0 | 45.4 | 51.6 |
-| <strong>DeepScaleR-1.5B-Preview</strong> | <strong>43.1</strong> | <strong>87.8</strong> | <strong>73.6</strong> | 30.2 | <strong>50.0</strong> | <strong>57.0</strong> |
-| <strong>DeepScaleR-1.5B-Preview-Reproduce</strong> | <strong>40.4</strong> | <strong>87.9</strong> | <strong>72.0</strong> | 31.5 | <strong>50.2</strong> | <strong>56.4</strong> |
 | O1-Preview | 40.0 | 81.4 | - | - | - | - |
 ## Citation
 ```bibtex
 @misc{deepscaler2025,

 ```
 ## Evaluation
 | Model | AIME 2024 | MATH 500 | AMC 2023 | Minerva Math | OlympiadBench | Avg. |
 |-------|-----------|-----------|-----------|--------------|---------------|------|
 | Qwen-2.5-7B-Instruct | 13.3 | 79.8 | 50.6 | 34.6 | 40.7 | 43.8 |
 | rStar-Math-7B | 26.7 | 78.4 | 47.5 | - | 47.1 | - |
 | Eurus-2-7B-PRIME | 26.7 | 79.2 | 57.8 | 38.6 | 42.1 | 48.9 |
+| Qwen2.5-7B-SimpleRL | 26.7 | 82.4 | 62.5 | 39.7 | 43.3 | 50.9 |
 | DeepSeek-R1-Distill-Qwen-1.5B | 28.8 | 82.8 | 62.9 | 26.5 | 43.3 | 48.9 |
 | Still-1.5B | 32.5 | 84.4 | 66.7 | 29.0 | 45.4 | 51.6 |
+| DeepScaleR-1.5B-Preview | 43.1 |87.8 |73.6 | 30.2 |50.0 |57.0 |
+| <strong>🎉 DeepScaleR-1.5B-Preview-Reproduce</strong> | 40.4 |87.9 | 72.0 | 31.5 | 50.2 |56.4|
 | O1-Preview | 40.0 | 81.4 | - | - | - | - |
 ## Citation
 ```bibtex
 @misc{deepscaler2025,