app.py

import gradio as gr
from transformers import pipeline, AutoTokenizer

# tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct")

# pipe = pipeline("text-generation", model="microsoft/Phi-3-mini-128k-instruct", trust_remote_code=True, tokenizer=tokenizer)
# gr.Interface.from_pipeline(pipe,
#                            title="TextGen",
#                            description="Using pipeline with Phi3",
#                            ).launch(inbrowser=True)

pipe = pipeline(
    "text-generation", 
    model="meta-llama/Meta-Llama-3-8B", 
    model_kwargs={"torch_dtype": torch.bfloat16}, 
    device_map="auto"
)

gr.Interface.from_pipeline(pipe,
                           title="TextGen",
                           description="Using pipeline with Llama3",
                           ).launch(inbrowser=True)