Instructions to use HINT-lab/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HINT-lab/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration with Transformers:

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

pipe = pipeline("text-generation", model="HINT-lab/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HINT-lab/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration")
model = AutoModelForCausalLM.from_pretrained("HINT-lab/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration", device_map="auto")
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 HINT-lab/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HINT-lab/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HINT-lab/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HINT-lab/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration

SGLang

How to use HINT-lab/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration 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 "HINT-lab/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration" \
    --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": "HINT-lab/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration",
		"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 "HINT-lab/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration" \
        --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": "HINT-lab/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HINT-lab/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration with Docker Model Runner:
```
docker model run hf.co/HINT-lab/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration
```

Improve model card with metadata and details

by nielsr HF Staff - opened Mar 6, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+47

-121

nielsr

Mar 6, 2025

This PR improves the model card by adding the necessary metadata (pipeline tag, library name, license) and populating some sections with information from the paper and GitHub README. It also adds relevant tags to improve searchability.

Improve model card with metadata and detailsface8cb6

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Cannot merge

This branch has merge conflicts in the following files:

README.md

· Sign up or log in to comment