Spaces:
Runtime error
Runtime error
File size: 1,191 Bytes
2185ead 361b22f 2185ead ffb6796 7e7d8a9 9e5e66c 4ee7dce 2185ead ffb6796 2185ead ffb6796 2185ead ffb6796 2185ead ffb6796 2185ead |
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 36 37 38 39 40 41 42 43 |
import os
import gradio as gr
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
# Read Hugging Face token from environment variable
HF_TOKEN = os.getenv("HF_TOKEN")
MODEL_NAME = "mistralai/Mistral-7B-v0.1"
print("Loading tokenizer and model...")
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, use_auth_token=HF_TOKEN)
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, use_auth_token=HF_TOKEN)
device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)
def generate_text(prompt):
inputs = tokenizer(prompt, return_tensors="pt").to(device)
outputs = model.generate(
**inputs,
max_length=150,
do_sample=True,
temperature=0.7,
top_p=0.9,
eos_token_id=tokenizer.eos_token_id
)
text = tokenizer.decode(outputs[0], skip_special_tokens=True)
return text
# Gradio UI
iface = gr.Interface(
fn=generate_text,
inputs=gr.Textbox(lines=5, placeholder="Enter your prompt here..."),
outputs="text",
title="TechChat - Mistral 7B",
description="Generate text with hari7261/TechChat model hosted on Hugging Face."
)
if __name__ == "__main__":
iface.launch()
|