app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

def generate(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=200)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

gr.Interface(fn=generate, inputs="text", outputs="text").launch()

# import gradio as gr
# from llama_cpp import Llama

# # Use the quantized model file path
# model_path = "MegaTom/TinyLlama-1.1B-Chat-v1.0-Q4_K_M-GGUF"  # Use your actual path to the quantized model

# # Load the quantized model
# llm = Llama(model_path=model_path)

# # Function to generate text using the model
# def generate(prompt):
#     # Generate the response
#     output = llm(prompt, max_tokens=50)
#     return output['choices'][0]['text']

# # Set up the Gradio interface
# gr.Interface(fn=generate, inputs="text", outputs="text").launch()