app.py

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

# Base model
base_model = "FreedomIntelligence/apollo-7b"  # Apollo 7B base
adapter_path = "Afsin-maahi/model" # replace with your repo name

# Load tokenizer and base model
tokenizer = AutoTokenizer.from_pretrained(base_model)
model = AutoModelForCausalLM.from_pretrained(base_model, torch_dtype=torch.float16, device_map="auto")

# Load LoRA/adapter
model = PeftModel.from_pretrained(model, adapter_path)

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

# Gradio interface
iface = gr.Interface(fn=chat, inputs="text", outputs="text", title="Apollo 7B Proxy Chat")
iface.launch()