Instructions to use OpenOneRec/OneRec-8B-pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenOneRec/OneRec-8B-pro with Transformers:

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

pipe = pipeline("text-generation", model="OpenOneRec/OneRec-8B-pro")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenOneRec/OneRec-8B-pro")
model = AutoModelForCausalLM.from_pretrained("OpenOneRec/OneRec-8B-pro")
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

vLLM

How to use OpenOneRec/OneRec-8B-pro with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/OpenOneRec/OneRec-8B-pro

SGLang

How to use OpenOneRec/OneRec-8B-pro 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 "OpenOneRec/OneRec-8B-pro" \
    --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": "OpenOneRec/OneRec-8B-pro",
		"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 "OpenOneRec/OneRec-8B-pro" \
        --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": "OpenOneRec/OneRec-8B-pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpenOneRec/OneRec-8B-pro with Docker Model Runner:
```
docker model run hf.co/OpenOneRec/OneRec-8B-pro
```

OpenOneRec commited on Jan 1

Commit

f077873

verified ·

1 Parent(s): b115428

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -197,7 +197,7 @@ The code in this repository is licensed under the Apache 2.0 License. The model
 OpenOneRec is built upon and inspired by the open-source ecosystem. We would like to thank:
 - **Qwen3**: for providing the base architecture and model initialization that OpenOneRec builds upon.
-- **General-domain data sources**: for the public corpora referenced in `data/general_text`(github链接) used for mixed-domain training.
 - **VeRL & PyTorch distributed training**: for the training infrastructure and scalable primitives (e.g., **FSDP**) used in post-training and large-scale runs.
 We sincerely thank these projects for their outstanding work.

 OpenOneRec is built upon and inspired by the open-source ecosystem. We would like to thank:
 - **Qwen3**: for providing the base architecture and model initialization that OpenOneRec builds upon.
+- **General-domain data sources**: for the public corpora referenced in [`data/general_text`](https://github.com/Kuaishou-OneRec/OpenOneRec/tree/main/data/general_text) used for mixed-domain training.
 - **VeRL & PyTorch distributed training**: for the training infrastructure and scalable primitives (e.g., **FSDP**) used in post-training and large-scale runs.
 We sincerely thank these projects for their outstanding work.