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
```

Random gibberish and endless gibberish appear after replying 1000-2000 characters.

by su400 - opened May 31, 2025

Discussion

su400

May 31, 2025

Random gibberish and endless gibberish appear after replying 1000-2000 characters. Here is my startup command.
RAY_IGNORE_UNHANDLED_ERRORS=1 python -m vllm.entrypoints.openai.api_server
--model /home/kkk/ai/models/DeepSeek-R1-0528-GPTQ
--tensor-parallel-size 8
--pipeline-parallel-size 2
--host 0.0.0.0
--port 9997
--enable-prefix-caching
--served-model-name DeepSeek-R1
--gpu-memory-utilization 0.95
--trust-remote-code
--max-num-batched-tokens 32768
--max-model-len 65535
--dtype float16

SpiridonSunRotator

IST Austria Distributed Algorithms and Systems Lab org May 31, 2025

@su400 which version of vLLM and compressed_tensors are you using?

SpiridonSunRotator

IST Austria Distributed Algorithms and Systems Lab org May 31, 2025

@su400 and by the way, which GPU? We observed that there are currently issues for execution on GB200. Execution on H100/H200 yields coherent outputs.

su400

May 31, 2025

vllm 0.9.1.dev85+g0f71e2403 /home/kkk/ai/vllm，compressed-tensors 0.9.4, 16X l40S.

su400

May 31, 2025

There's no problem now. I switched to VLLM 0.9.01, but the speed is slower than the original R1 AWQ version. The same machine used to have 40 tokens per second, but now it has 30 tokens per second. The reason for VLLM optimization should also be attributed.

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