Instructions to use ISTA-DASLab/DeepSeek-R1-Distill-Qwen-32B-HIGGS-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ISTA-DASLab/DeepSeek-R1-Distill-Qwen-32B-HIGGS-4bit with Transformers:

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

pipe = pipeline("text-generation", model="ISTA-DASLab/DeepSeek-R1-Distill-Qwen-32B-HIGGS-4bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ISTA-DASLab/DeepSeek-R1-Distill-Qwen-32B-HIGGS-4bit")
model = AutoModelForCausalLM.from_pretrained("ISTA-DASLab/DeepSeek-R1-Distill-Qwen-32B-HIGGS-4bit")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ISTA-DASLab/DeepSeek-R1-Distill-Qwen-32B-HIGGS-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ISTA-DASLab/DeepSeek-R1-Distill-Qwen-32B-HIGGS-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ISTA-DASLab/DeepSeek-R1-Distill-Qwen-32B-HIGGS-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ISTA-DASLab/DeepSeek-R1-Distill-Qwen-32B-HIGGS-4bit

SGLang

How to use ISTA-DASLab/DeepSeek-R1-Distill-Qwen-32B-HIGGS-4bit 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 "ISTA-DASLab/DeepSeek-R1-Distill-Qwen-32B-HIGGS-4bit" \
    --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": "ISTA-DASLab/DeepSeek-R1-Distill-Qwen-32B-HIGGS-4bit",
		"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 "ISTA-DASLab/DeepSeek-R1-Distill-Qwen-32B-HIGGS-4bit" \
        --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": "ISTA-DASLab/DeepSeek-R1-Distill-Qwen-32B-HIGGS-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ISTA-DASLab/DeepSeek-R1-Distill-Qwen-32B-HIGGS-4bit with Docker Model Runner:
```
docker model run hf.co/ISTA-DASLab/DeepSeek-R1-Distill-Qwen-32B-HIGGS-4bit
```

how to quantize this model?

by NEWWWWWbie - opened Apr 15, 2025

Discussion

NEWWWWWbie

Apr 15, 2025

Hi,
Can I ask how you guys are quantizing the DeepSeek Distill Qwen 32B model using HIGGS?

I tried using the following config directly, but the output seems broken

model_name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
higgs_config = HiggsConfig(
bits=4,
group_size=128,
damp_percent=0.01,
modules_to_not_convert=[],
desc_act=True,
scale_dtype="fp16",
block_name_to_quantize="all",
optimize_target="latency",
)
model = AutoModelForCausalLM.from_pretrained(
model_name,
quantization_config=higgs_config,
torch_dtype=torch.bfloat16,
device_map="auto"
)

tokenizer = AutoTokenizer.from_pretrained(model_name)

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment