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

Libraries

How to use QuantFactory/DeepScaleR-1.5B-Preview-GGUF with Transformers:

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

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

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

llama-cpp-python

How to use QuantFactory/DeepScaleR-1.5B-Preview-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/DeepScaleR-1.5B-Preview-GGUF",
	filename="DeepScaleR-1.5B-Preview.Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use QuantFactory/DeepScaleR-1.5B-Preview-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/DeepScaleR-1.5B-Preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/DeepScaleR-1.5B-Preview-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/DeepScaleR-1.5B-Preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/DeepScaleR-1.5B-Preview-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf QuantFactory/DeepScaleR-1.5B-Preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/DeepScaleR-1.5B-Preview-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf QuantFactory/DeepScaleR-1.5B-Preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/DeepScaleR-1.5B-Preview-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/DeepScaleR-1.5B-Preview-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/DeepScaleR-1.5B-Preview-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/QuantFactory/DeepScaleR-1.5B-Preview-GGUF:Q4_K_M

SGLang

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

Ollama
How to use QuantFactory/DeepScaleR-1.5B-Preview-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/DeepScaleR-1.5B-Preview-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/DeepScaleR-1.5B-Preview-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for QuantFactory/DeepScaleR-1.5B-Preview-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for QuantFactory/DeepScaleR-1.5B-Preview-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/DeepScaleR-1.5B-Preview-GGUF to start chatting

Docker Model Runner
How to use QuantFactory/DeepScaleR-1.5B-Preview-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/DeepScaleR-1.5B-Preview-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/DeepScaleR-1.5B-Preview-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/DeepScaleR-1.5B-Preview-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DeepScaleR-1.5B-Preview-GGUF-Q4_K_M

List all available models

lemonade list

munish0838 commited on Apr 12, 2025

Commit

8af7fa8

verified ·

1 Parent(s): f17fc23

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +4 -3

README.md CHANGED Viewed

@@ -12,6 +12,7 @@ language:
 - en
 base_model:
 - deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
 ---
@@ -32,7 +33,7 @@ This is quantized version of [agentica-org/DeepScaleR-1.5B-Preview](https://hugg
 </div>
 <br>
 <div align="center" style="line-height: 1;">
-  <a href="https://github.com/agentica-project/deepscaler" style="margin: 2px;">
     <img alt="Code" src="https://img.shields.io/badge/DeepScaleR-000000?style=for-the-badge&logo=github&logoColor=000&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
   </a>
   <a href="https://pretty-radio-b75.notion.site/DeepScaleR-Surpassing-O1-Preview-with-a-1-5B-Model-by-Scaling-RL-19681902c1468005bed8ca303013a4e2" target="_blank" style="margin: 2px;">
@@ -86,7 +87,7 @@ A more detailed description of the training recipe can be found in our [blog pos
 We report Pass@1 accuracy averaged over 16 samples for each problem.
 | Model | AIME 2024 | MATH 500 | AMC 2023 | Minerva Math | OlympiadBench | Avg. |
 |-------|-----------|-----------|-----------|--------------|---------------|------|
-| 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 |
@@ -118,7 +119,7 @@ This permissive license ensures that researchers, developers, and enthusiasts wo
 ```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 Tang and Manan Roongta and Colin Cai and Jeffrey Luo and Tianjun Zhang and 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}

 - en
 base_model:
 - deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+pipeline_tag: text-generation
 ---
 </div>
 <br>
 <div align="center" style="line-height: 1;">
+  <a href="https://github.com/agentica-project/rllm" style="margin: 2px;">
     <img alt="Code" src="https://img.shields.io/badge/DeepScaleR-000000?style=for-the-badge&logo=github&logoColor=000&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
   </a>
   <a href="https://pretty-radio-b75.notion.site/DeepScaleR-Surpassing-O1-Preview-with-a-1-5B-Model-by-Scaling-RL-19681902c1468005bed8ca303013a4e2" target="_blank" style="margin: 2px;">
 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 |
 ```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 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}