GE-LLM-APP / readme.md
Motunrayo1960422's picture
Upload folder using huggingface_hub
f4cd5ad verified
|
Raw
History Blame Contribute Delete
245 Bytes

A newer version of the Gradio SDK is available: 6.19.0

Upgrade

Run Server

vllm serve "Motunrayo1960422/text-to-GreatExpectation-llama-finetuned-v1" --max_model_len 56000 --gpu_memory_utilization 0.95

Run App

  • docker build -t ge-app:latest
  • docker run -p 7860:7860 gradio-app:latest