Instructions to use cx-cmu/repro-rephraser-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cx-cmu/repro-rephraser-4B with Transformers:

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

pipe = pipeline("text-generation", model="cx-cmu/repro-rephraser-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cx-cmu/repro-rephraser-4B")
model = AutoModelForCausalLM.from_pretrained("cx-cmu/repro-rephraser-4B", 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 cx-cmu/repro-rephraser-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cx-cmu/repro-rephraser-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cx-cmu/repro-rephraser-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cx-cmu/repro-rephraser-4B

SGLang

How to use cx-cmu/repro-rephraser-4B 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 "cx-cmu/repro-rephraser-4B" \
    --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": "cx-cmu/repro-rephraser-4B",
		"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 "cx-cmu/repro-rephraser-4B" \
        --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": "cx-cmu/repro-rephraser-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cx-cmu/repro-rephraser-4B with Docker Model Runner:
```
docker model run hf.co/cx-cmu/repro-rephraser-4B
```

Improve model card: Add pipeline tag, library, license, and links

by nielsr HF Staff - opened Oct 14, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+10

-5

nielsr

Oct 14, 2025

This PR enhances the model card for cx-cmu/repro-rephraser-4B by:

Adding pipeline_tag: text-generation to improve discoverability for rephrasing tasks.
Including library_name: transformers based on the model's architecture (Qwen3ForCausalLM and transformers_version in config.json), which enables the automated "How to use" code snippet.
Adding license: cc-by-nc-4.0 to clarify usage terms.
Updating the paper reference in the initial description to link directly to the Hugging Face Papers page: RePro: Training Language Models to Faithfully Recycle the Web for Pretraining.
Adding an explicit link to the GitHub repository (https://github.com/cxcscmu/RePro) in the main content.

These changes provide more comprehensive and structured information for users and align the model card with best practices on the Hub.

Improve model card: Add pipeline tag, library, license, and links21f4edd4

yuzc19

Chenyan Xiong Research Group at CMU org Oct 18, 2025

Thank you for your PR!

yuzc19 changed pull request status to merged Oct 18, 2025

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