Delete app.py

app.py

@@ -1,52 +0,0 @@
- import os
-import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
-import torch
-
-# Load model from environment variable or fallback
-model_id = os.getenv("MODEL_ID", "TheBloke/Mistral-7B-Instruct-v0.3-GPTQ")
-
-# Load tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    device_map="auto",
-    torch_dtype=torch.float16,
-)
-
-# Initialize streamer for live output
-streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
-
-# Define the chat function
-def chat(message, history):
-    history = history or []
-    conversation = history + [(message, "")]
-
-    prompt = tokenizer.apply_chat_template(
-        conversation,
-        tokenize=False,
-        add_generation_prompt=True
-    )
-
-    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-
-    with torch.no_grad():
-        output_ids = model.generate(
-            **inputs,
-            max_new_tokens=512,
-            do_sample=True,
-            temperature=0.7,
-            top_p=0.95,
-        )
-
-    decoded = tokenizer.decode(output_ids[0], skip_special_tokens=True)
-    reply = decoded.split(message)[-1].strip()
-
-    return reply
-
-# Build Gradio UI
-interface = gr.ChatInterface(fn=chat, title="🧠 Vynix AI")
-
-# Launch App
-if _name_ == "_main_":
-    interface.launch()