first commit

app.py

@@ -1,14 +1,12 @@
 import streamlit as st
-import torch
 # Load model directly
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-model_open_chat = AutoModelForCausalLM.from_pretrained("openchat/openchat_3.5",
-                                                       device_map="auto", temperature=0.1,torch_dtype=torch.bfloat16)
-tokenizer_open_chat = AutoTokenizer.from_pretrained("openchat/openchat_3.5")
+tokenizer = AutoTokenizer.from_pretrained("openchat/openchat")
+model = AutoModelForCausalLM.from_pretrained("openchat/openchat")
 prompt = ""
-model_input = tokenizer_open_chat(prompt, return_tensors="pt").to("cuda")
-response = tokenizer_open_chat.decode(model_open_chat.generate(**model_input,temperature=0.1, max_length=5000)[0], skip_special_tokens=True)
+model_input = tokenizer(prompt, return_tensors="pt").to("cuda")
+response = tokenizer.decode(model.generate(**model_input,temperature=0.1, max_length=5000)[0], skip_special_tokens=True)
 
 prompt = st.chat_input("Say something")
 if prompt: