How to use from
vLLM
Install from pip and serve model
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NingLab/eCeLLM-S"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NingLab/eCeLLM-S",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'
Use Docker
docker model run hf.co/NingLab/eCeLLM-S
Quick Links

eCeLLM-S

This repo contains the models for "eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data"

eCeLLM Models

Leveraging ECInstruct, we develop eCeLLM by instruction tuning general-purpose LLMs (base models). The eCeLLM-S model is instruction-tuned from the large base models Phi-2.

Citation

@inproceedings{
    peng2024ecellm,
    title={eCe{LLM}: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data},
    author={Bo Peng and Xinyi Ling and Ziru Chen and Huan Sun and Xia Ning},
    booktitle={Forty-first International Conference on Machine Learning},
    year={2024},
    url={https://openreview.net/forum?id=LWRI4uPG2X}
}
Downloads last month
126
Safetensors
Model size
3B params
Tensor type
F16
·
Inference Providers NEW

Dataset used to train NingLab/eCeLLM-S