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

Libraries

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

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

pipe = pipeline("text-generation", model="ldwang/DeepScaleR-1.5B-Preview-Reproduce")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ldwang/DeepScaleR-1.5B-Preview-Reproduce", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ldwang/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 "ldwang/DeepScaleR-1.5B-Preview-Reproduce"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ldwang/DeepScaleR-1.5B-Preview-Reproduce",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use ldwang/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 "ldwang/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/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ldwang/DeepScaleR-1.5B-Preview-Reproduce",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ldwang/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/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ldwang/DeepScaleR-1.5B-Preview-Reproduce",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

ldwang commited on May 19, 2025

Commit

3d8a174

verified ·

1 Parent(s): 1448e50

Create README.md

Browse files

Files changed (1) hide show

README.md +65 -0

README.md ADDED Viewed

	@@ -0,0 +1,65 @@

+---
+license: mit
+library_name: transformers
+datasets:
+- AI-MO/NuminaMath-CoT
+- KbsdJames/Omni-MATH
+- RUC-AIBOX/STILL-3-Preview-RL-Data
+- hendrycks/competition_math
+language:
+- en
+base_model:
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+pipeline_tag: text-generation
+---
+<span style="font-family: default; font-size: 1.5em;">DeepScaleR-1.5B-Preview-Reproduce</span>
+## Overview
+This model is a reproduction of the [agentica-project/deepscaler](https://github.com/agentica-project/deepscaler) project.
+We have reproduced the results in the repo on an **8x80G** node, achieving an average score of **TBU**.
+## Training
+```bash
+export VLLM_ATTENTION_BACKEND=XFORMERS
+# Run 8K context length training, 580 steps
+export MODEL_PATH="deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
+nohup bash run_deepscaler_1.5b_8k.sh --model $MODEL_PATH > stage1.log 2>&1 &
+# Run 16K context length training, 430 steps
+export MODEL_PATH="./checkpoints/deepscaler/deepscaler-1.5b-8k/actor/global_step_580"
+nohup bash run_deepscaler_1.5b_16k.sh --model $MODEL_PATH > stage2.log 2>&1 &
+# Run 24K context length training, 430 steps
+export MODEL_PATH="./checkpoints/deepscaler/deepscaler-1.5b-16k/actor/global_step_430"
+nohup bash run_deepscaler_1.5b_24k.sh --model $MODEL_PATH > stage3.log 2>&1 &
+```
+## 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 |
+| [DeepScaleR-1.5B-Preview-Reproduce](https://huggingface.co/junnyu/DeepScaleR-1.5B-Preview-Reproduce) | 40.4 |87.9 | 72.0 | 31.5 | 50.2 |56.4|
+| <strong>🎉 DeepScaleR-1.5B-Preview-Reproduce</strong> | 42.3 |- | - | - | - |-|
+| O1-Preview | 40.0 | 81.4 | - | - | - | - |
+## Citation
+```bibtex
+@misc{deepscaler2025,
+  title={DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL},
+  author={Michael Luo and Sijun Tan and Justin Wong and Xiaoxiang Shi and William Y. Tang and Manan Roongta and Colin Cai and Jeffrey Luo and Tianjun Zhang and Li Erran Li and Raluca Ada Popa and Ion Stoica},
+  year={2025},
+  howpublished={\url{https://pretty-radio-b75.notion.site/DeepScaleR-Surpassing-O1-Preview-with-a-1-5B-Model-by-Scaling-RL-19681902c1468005bed8ca303013a4e2}},
+  note={Notion Blog}
+  year={2025}
+}