first commit

app.py

@@ -1,4 +1,19 @@
 import streamlit as st
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-x = st.slider('Select a value')
-st.write(x, 'squared is', x * x)
+tokenizer = AutoTokenizer.from_pretrained("openchat/openchat_3.5")
+model = AutoModelForCausalLM.from_pretrained("openchat/openchat_3.5")
+
+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")
+
+prompt = st.chat_input("Say something")
+if prompt:
+    st.write(f"User has sent the following prompt: {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)
+
+print(response)