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 Settings

vLLM

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

SGLang

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
```

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

by KrishnaKaasyap - opened Jan 20, 2025

Discussion

KrishnaKaasyap

Jan 20, 2025

I'm amazed to see just SFT is making Llama 3.3 70B look like a SOTA model!

Imagine what Meta is cooking with 200k H100s for Llama 4!

Smol models using R1 reasoning chains are awesome!

Is there the dataset used to distill these models available for replication anywhere? I couldn't find any in the official documentation!

perelmanych

Jan 21, 2025

I wonder why they didn't distill Qwen 2.5 72B, as it is even better in reasoning tasks than Llama 3.3 70B. That would be really nice.

DataSoul

Jan 22, 2025

I wonder why they didn't distill Qwen 2.5 72B, as it is even better in reasoning tasks than Llama 3.3 70B. That would be really nice.

I guess it might be because of "License".

gghfez

Jan 26, 2025

I guess it might be because of "License".

@DataSoul I doubt it, they didn't comply with the Llama3 license here right (the derived model name has to start with Llama), and they've slapped an MIT license on this one (I believe it'd inherit the Meta license).

I wonder why they didn't distill Qwen 2.5 72B, as it is even better in reasoning tasks than Llama 3.3 70B

I can only speculate but, they've effectively taught Llama3.3 how to reason properly without actually giving it any knew knowledge. In my experience, Llama 3.3 has more general knowledge than Qwen2.5 when prompted correctly.

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