deepseek-ai
/

DeepSeek-R1-Distill-Llama-70B

Text Generation

text-generation-inference

Model card Files Files and versions

Instructions to use deepseek-ai/DeepSeek-R1-Distill-Llama-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-R1-Distill-Llama-70B with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-R1-Distill-Llama-70B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Llama-70B")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Llama-70B")
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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

How to use deepseek-ai/DeepSeek-R1-Distill-Llama-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-R1-Distill-Llama-70B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B

How to use deepseek-ai/DeepSeek-R1-Distill-Llama-70B 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 "deepseek-ai/DeepSeek-R1-Distill-Llama-70B" \
    --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": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
		"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 "deepseek-ai/DeepSeek-R1-Distill-Llama-70B" \
        --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": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-R1-Distill-Llama-70B with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
```

Resources

View closed (2)

Add card sections: Description, Intended use, Limitations, How to use

#31 opened about 14 hours ago by

Upload figures/benchmark.jpg with huggingface_hub

#30 opened about 14 hours ago by

Upload config.json with huggingface_hub

#29 opened about 14 hours ago by

Upload README.md with huggingface_hub

#28 opened about 14 hours ago by

Upload LICENSE with huggingface_hub

#27 opened about 14 hours ago by

Upload model files and documentation

#26 opened about 16 hours ago by

Fix chat_template crash when assistant message omits the `content` key

#25 opened 10 days ago by

I built a unified wrapper for llmcompressor, llama.cpp & coremltools. Looking for LLM users to help me break it!

#24 opened 2 months ago by

Update README.md

#23 opened 4 months ago by

Create Zeng

#22 opened 5 months ago by

Tool Use

#21 opened about 1 year ago by

使用llama-factory训练70B最低的硬件配置是什么？

#20 opened about 1 year ago by

Do not require reasoning but just the ouput

#19 opened about 1 year ago by

chat_template中为什么要把assistant角色中的<think>过程切掉

#18 opened about 1 year ago by

能否发布一个awq版本的模型：deepseek-r1-distill-llama-70b-AWQ

#17 opened about 1 year ago by

Update README.md

#16 opened about 1 year ago by

shubham-kothari

chnsmth

#15 opened about 1 year ago by

Does DeepSeek-Llama-70B support tensor parallelism for multi-GPU inference?

#14 opened over 1 year ago by

weight files naming is not regular rule

#13 opened over 1 year ago by

How much vram do you need?

#12 opened over 1 year ago by

Upload IMG_4815.jpeg

#11 opened over 1 year ago by

Amazon Sagemaker deployment failing with CUDA OutOfMemory error

#10 opened over 1 year ago by

<thinking> is the proper tag?

#8 opened over 1 year ago by

Add pipeline tag

#7 opened over 1 year ago by

Template

#6 opened over 1 year ago by

Lora

#4 opened over 1 year ago by

SFT (Non-RL) distillation is this good on a sub-100B model?

#2 opened over 1 year ago by

Lfg

#1 opened over 1 year ago by