Update app.py

app.py

@@ -4,7 +4,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStream
 import gradio as gr
 from threading import Thread
 
-MODEL = "tiiuae/falcon3-7b-1.58bit"
+MODEL = "tiiuae/falcon3-7b-instruct-1.58bit"
 
 TITLE = "<h1><center>Falcon3-1.58 bit playground</center></h1>"
 SUB_TITLE = """<center>This interface has been created for quick validation purposes, do not use it for production. Bear also in mind the model is a pretrained model.</center>"""
@@ -46,7 +46,20 @@ def stream_chat(
     penalty: float = 1.2,
 ):
     print(f'message: {message}')
-    inputs = tokenizer.encode(message, return_tensors="pt").to(device)
+    print(f'history: {history}')
+
+    conversation = []
+    for prompt, answer in history:
+        conversation.extend([
+            {"role": "user", "content": prompt}, 
+            {"role": "assistant", "content": answer},
+        ])
+
+
+    conversation.append({"role": "user", "content": message})
+    input_text = tokenizer.apply_chat_template(conversation, tokenize=False, add_generation_prompt = True)
+        
+    inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
     streamer = TextIteratorStreamer(tokenizer, timeout=60.0, skip_prompt=True, skip_special_tokens=True)
     
     generate_kwargs = dict(