Instructions to use thu-pacman/Puro-2B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thu-pacman/Puro-2B-Base with Transformers:

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

pipe = pipeline("text-generation", model="thu-pacman/Puro-2B-Base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("thu-pacman/Puro-2B-Base")
model = AutoModelForCausalLM.from_pretrained("thu-pacman/Puro-2B-Base", 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 thu-pacman/Puro-2B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thu-pacman/Puro-2B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thu-pacman/Puro-2B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thu-pacman/Puro-2B-Base

SGLang

How to use thu-pacman/Puro-2B-Base 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 "thu-pacman/Puro-2B-Base" \
    --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": "thu-pacman/Puro-2B-Base",
		"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 "thu-pacman/Puro-2B-Base" \
        --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": "thu-pacman/Puro-2B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thu-pacman/Puro-2B-Base with Docker Model Runner:
```
docker model run hf.co/thu-pacman/Puro-2B-Base
```

Puro-2B-Base

Commit History

Delete Puro-Technical-Report.pdf

b434d9e
verified

harryleafchen commited on 2 days ago

Show release URLs in model card

03c716f

Yaorui Yin commited on 4 days ago

Update report figures

9b9d28e

Yaorui Yin commited on 4 days ago

Update model card

f8702d8

Yaorui Yin commited on 4 days ago

docs: add arXiv reference in README

3cd9c0d
verified

harryleafchen commited on 6 days ago

Upload Puro-Technical-Report.pdf

2ccf5b9
verified

openhonor commited on 12 days ago

docs: update figure widths in README

817fe13
verified

harryleafchen commited on 13 days ago

docs: update README on arXiv status

12558ff
verified

harryleafchen commited on 13 days ago

Update README.md

cfa7a5a
verified

openhonor commited on 13 days ago

Update README.md

5901893
verified

openhonor commited on 13 days ago

Upload 6 files

6995ad6
verified

openhonor commited on 13 days ago

Update LICENSE

4fb96a4
verified

harryleafchen commited on 18 days ago

Create LICENSE

f7c606d
verified

harryleafchen commited on 18 days ago

Update README.md

2adc85d
verified

harryleafchen commited on 18 days ago

Update README.md

bc210a6
verified

harryleafchen commited on 18 days ago

Upload folder using huggingface_hub

cd3f91d
verified

harryleafchen commited on 18 days ago

initial commit

0c64cd3
verified

harryleafchen commited on 18 days ago

Commit History

Delete Puro-Technical-Report.pdf b434d9e verified

Show release URLs in model card 03c716f

Update report figures 9b9d28e

Update model card f8702d8

docs: add arXiv reference in README 3cd9c0d verified

Upload Puro-Technical-Report.pdf 2ccf5b9 verified

docs: update figure widths in README 817fe13 verified

docs: update README on arXiv status 12558ff verified

Update README.md cfa7a5a verified

Update README.md 5901893 verified

Upload 6 files 6995ad6 verified

Update LICENSE 4fb96a4 verified

Create LICENSE f7c606d verified

Update README.md 2adc85d verified

Update README.md bc210a6 verified

Upload folder using huggingface_hub cd3f91d verified

initial commit 0c64cd3 verified

Delete Puro-Technical-Report.pdf

b434d9e
verified

Show release URLs in model card

03c716f

Update report figures

9b9d28e

Update model card

f8702d8

docs: add arXiv reference in README

3cd9c0d
verified

Upload Puro-Technical-Report.pdf

2ccf5b9
verified

docs: update figure widths in README

817fe13
verified

docs: update README on arXiv status

12558ff
verified

Update README.md

cfa7a5a
verified

Update README.md

5901893
verified

Upload 6 files

6995ad6
verified

Update LICENSE

4fb96a4
verified

Create LICENSE

f7c606d
verified

Update README.md

2adc85d
verified

Update README.md

bc210a6
verified

Upload folder using huggingface_hub

cd3f91d
verified

initial commit

0c64cd3
verified