app.py

from transformers import AutoModelForCausalLM, AutoTokenizer
import gradio as gr
import torch

model_id = "saikrishnagorijala/friday-V1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")

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

demo = gr.Interface(fn=chat, inputs="text", outputs="text", title="Friday-V1")
demo.launch()