Instructions to use QuixiAI/DeepSeek-R1-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuixiAI/DeepSeek-R1-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="QuixiAI/DeepSeek-R1-AWQ", 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("QuixiAI/DeepSeek-R1-AWQ", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("QuixiAI/DeepSeek-R1-AWQ", 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

vLLM

How to use QuixiAI/DeepSeek-R1-AWQ with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/QuixiAI/DeepSeek-R1-AWQ

SGLang

How to use QuixiAI/DeepSeek-R1-AWQ 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 "QuixiAI/DeepSeek-R1-AWQ" \
    --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": "QuixiAI/DeepSeek-R1-AWQ",
		"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 "QuixiAI/DeepSeek-R1-AWQ" \
        --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": "QuixiAI/DeepSeek-R1-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use QuixiAI/DeepSeek-R1-AWQ with Docker Model Runner:
```
docker model run hf.co/QuixiAI/DeepSeek-R1-AWQ
```

Smaller deepseek models?

by loshka2 - opened Jan 22, 2025

Discussion

loshka2

Jan 22, 2025

Are you planning on preparing 7B Qwen DeepSeek R1 or 8B Llama DeepSeek R1 as well?
Would be perfect for ollama. I would even tip you a hundred bucks in btc it if I could run one of these this week.

v2ray

Jan 23, 2025

https://huggingface.co/collections/casperhansen/deepseek-r1-awq-6790b746ef7540cfbb0f0331

loshka2

Jan 23, 2025

https://huggingface.co/collections/casperhansen/deepseek-r1-awq-6790b746ef7540cfbb0f0331

Sorry, is this a Dolphin version? Or another "uncensored" one?

Could you please push your builds to Ollama repository? So a page like this appears: https://ollama.com/CognitiveComputations

v2ray

Jan 24, 2025

No, they are the original version.

devops724

Jan 27, 2025

can you share awq command you use for convert this model to awq version,please ?

loshka2

Jan 28, 2025

The demand for uncensored deepseek model everyone could use at home is huge. Is there any progress here?

loshka2

Jan 28, 2025

Apparently this is not even a Dolphin version yet, just a pure fork of R1.
Yet, I've found another author publishing an "abliterated" version here: https://huggingface.co/collections/huihui-ai/deepseek-r1-abliterated-6790ea12ce8c8c4e5df51b7f

loshka2 changed discussion status to closed Jan 28, 2025

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