Instructions to use Anonymous123456789111213/Deepseek-R1-DistillLlama-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Anonymous123456789111213/Deepseek-R1-DistillLlama-8b with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Llama-8B")
model = PeftModel.from_pretrained(base_model, "Anonymous123456789111213/Deepseek-R1-DistillLlama-8b")

Transformers

How to use Anonymous123456789111213/Deepseek-R1-DistillLlama-8b with Transformers:

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

pipe = pipeline("text-generation", model="Anonymous123456789111213/Deepseek-R1-DistillLlama-8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Anonymous123456789111213/Deepseek-R1-DistillLlama-8b", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Anonymous123456789111213/Deepseek-R1-DistillLlama-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Anonymous123456789111213/Deepseek-R1-DistillLlama-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Anonymous123456789111213/Deepseek-R1-DistillLlama-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Anonymous123456789111213/Deepseek-R1-DistillLlama-8b

SGLang

How to use Anonymous123456789111213/Deepseek-R1-DistillLlama-8b 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 "Anonymous123456789111213/Deepseek-R1-DistillLlama-8b" \
    --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": "Anonymous123456789111213/Deepseek-R1-DistillLlama-8b",
		"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 "Anonymous123456789111213/Deepseek-R1-DistillLlama-8b" \
        --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": "Anonymous123456789111213/Deepseek-R1-DistillLlama-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Anonymous123456789111213/Deepseek-R1-DistillLlama-8b with Docker Model Runner:
```
docker model run hf.co/Anonymous123456789111213/Deepseek-R1-DistillLlama-8b
```

Deepseek-R1-DistillLlama-8b / tokenizer.json

Anonymous123456789111213

Upload folder using huggingface_hub

bc9cc5c verified about 2 months ago

download

history blame contribute delete

17.2 MB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 2367f89aa008201d112f4575da402eda44d01cf4fc475d0e4ebbcb8d0d255f13
Size of remote file:: 17.2 MB
SHA256:: 37034cd133dfeac08b4f0cbc5f2ae86fa5db1b1d3b8700644bbfdae9355736c0

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.