Instructions to use ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts with Transformers:

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

pipe = pipeline("text-generation", model="ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts", trust_remote_code=True)
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 ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts

SGLang

How to use ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts 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-R1-0528-GPTQ-4b-128g-experts" \
    --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": "ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts",
		"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 "ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts" \
        --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": "ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts with Docker Model Runner:
```
docker model run hf.co/ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts
```

DeepSeek-R1-0528-GPTQ-4b-128g-experts

Model Overview

This model was obtained by quantizing the weights of deepseek-ai/DeepSeek-R1-0528 to INT4 data type. This optimization reduces the number of bits per parameter from 8 to 4, reducing the disk size and GPU memory requirements by approximately 50%.

Only non-shared experts within transformer blocks are compressed. Weights are quantized using a symmetric per-group scheme, with group size 128. The GPTQ algorithm is applied for quantization.

Model checkpoint is saved in compressed_tensors format.

Evaluation

This model was evaluated on reasoning tasks (AIME-24, GPQA-Diamond, MATH-500).

Model outputs were generated with the vLLM engine.

For reasoning tasks we estimate pass@1 based on 10 runs with different seeds and temperature=0.6, top_p=0.95 and max_new_tokens=65536.

	Recovery (%)	deepseek/DeepSeek-R1-0528	ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts (this model)
AIME 2024 pass@1	98.50	88.66	87.33
MATH-500 pass@1	99.88	97.52	97.40
GPQA Diamond pass@1	101.21	79.65	80.61
Reasoning Average Score	99.82	88.61	88.45

Contributors

Denis Kuznedelev (Yandex), Eldar Kurtić (Red Hat AI & ISTA), and Dan Alistarh (Red Hat AI & ISTA).

Downloads last month: 10

Safetensors

Model size

676B params

Tensor type

BF16

I64

F32

I32