File size: 1,087 Bytes
453736e ea09339 368243d 453736e ea09339 df632f9 453736e ea09339 |
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 gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
import os
# Log CPU info at startup
cpu_info = os.popen("cat /proc/cpuinfo | grep 'model name' | head -1").read().strip()
print(f"🖥️ Running on: {cpu_info}")
# Pick any model you want to test (small for free Spaces)
MODEL_ID = "LiquidAI/LFM2-1.2B"
# Load tokenizer + model
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModelForCausalLM.from_pretrained(
MODEL_ID,
torch_dtype=torch.float32, # use float32 for CPU (no GPU)
)
def chat_with_ai(user_input):
inputs = tokenizer(user_input, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
return response
demo = gr.Interface(
fn=chat_with_ai,
inputs=gr.Textbox(label="Your Message"),
outputs=gr.Textbox(label="AI Response"),
title="Test AI Chat Model",
description="Type a message to chat with an LLM hosted on Hugging Face."
)
demo.launch(server_name="0.0.0.0", server_port=7860)
|