Instructions to use OpenOneRec/OneReason-0.8B-pretrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenOneRec/OneReason-0.8B-pretrain with Transformers:

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

pipe = pipeline("text-generation", model="OpenOneRec/OneReason-0.8B-pretrain")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("OpenOneRec/OneReason-0.8B-pretrain")
model = AutoModelForMultimodalLM.from_pretrained("OpenOneRec/OneReason-0.8B-pretrain")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenOneRec/OneReason-0.8B-pretrain with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenOneRec/OneReason-0.8B-pretrain"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenOneRec/OneReason-0.8B-pretrain",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenOneRec/OneReason-0.8B-pretrain

SGLang

How to use OpenOneRec/OneReason-0.8B-pretrain 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/OneReason-0.8B-pretrain" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenOneRec/OneReason-0.8B-pretrain",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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/OneReason-0.8B-pretrain" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenOneRec/OneReason-0.8B-pretrain",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenOneRec/OneReason-0.8B-pretrain with Docker Model Runner:
```
docker model run hf.co/OpenOneRec/OneReason-0.8B-pretrain
```

OpenOneRec commited on 1 day ago

Commit

d498b25

verified ·

1 Parent(s): bc470b4

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -3,7 +3,6 @@ language:
 - en
 - zh
 library_name: transformers
-pipeline_tag: text-generation
 tags:
 - recommendation
 - generative-recommendation
@@ -11,6 +10,7 @@ tags:
 - itemic-token
 - qwen3
 - pretraining
 ---
 # OneReason
@@ -335,4 +335,4 @@ Please refer to the license file in this repository for the terms governing the
 ## Acknowledgements
-OneReason builds on the open-source LLM and recommendation ecosystem. We thank the Qwen, OpenOneRec, PyTorch, Transformers, and distributed training communities for their foundational contributions.

 - en
 - zh
 library_name: transformers
 tags:
 - recommendation
 - generative-recommendation
 - itemic-token
 - qwen3
 - pretraining
+license: apache-2.0
 ---
 # OneReason
 ## Acknowledgements
+OneReason builds on the open-source LLM and recommendation ecosystem. We thank the Qwen, OpenOneRec, PyTorch, Transformers, and distributed training communities for their foundational contributions.