Update app.py

app.py

@@ -1,18 +1,16 @@
 from fastapi import FastAPI
 import uvicorn
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
 model_name = "DavidAU/Llama-3.2-4X3B-MOE-Hell-California-Uncensored-10B-GGUF"
 
-from transformers import AutoModel, AutoTokenizer, TextStreamer
-import torch
-
 # Load model and tokenizer
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModel.from_pretrained(
-    model_name,
-    device_map="auto",
-    trust_remote_code=True
-)
+
+model_id = "TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF"
+filename = "tinyllama-1.1b-chat-v1.0.Q6_K.gguf"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id, gguf_file=filename)
+model = AutoModelForCausalLM.from_pretrained(model_id, gguf_file=filename)
 
 def llama2_chat(prompt):
     inputs = tokenizer(input_text, return_tensors="pt", padding=True, truncation=True)