File size: 808 Bytes
ce4b75d 686678a e86ad04 951adef d690585 6a968bc 951adef 6a968bc fc6d403 6a968bc 951adef 686678a 6a968bc 498e38f 6a968bc 26a2377 951adef 686678a 6a968bc 951adef 686678a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 |
import os
import spaces
import torch
import transformers
import gradio as gr
access_token = os.environ["HF_ACCESS_TOKEN"]
model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
token=access_token
)
@spaces.GPU
def generate_text(input_text):
prompt = {"role": "system", "content": "Summarize the following: "+input_text}
output = pipeline(prompt,
max_new_tokens=256,
)
return output
iface = gr.Interface(
fn=generate_text,
inputs=gr.Textbox(placeholder="Enter prompt..."),
outputs="text",
title="LLaMA 3 8B Text Generation"
)
iface.launch(server_name="0.0.0.0", server_port=7860) |