Update app.py

app.py

@@ -12,7 +12,49 @@ import atexit
 import subprocess
 from urllib.parse import urlparse, quote
 import webbrowser
-
+import spaces
+
+device = "cuda"
+
+@spaces.GPU()
+def stream_chat(
+    message: str,
+    history: list,
+    system_prompt: str,
+    temperature: float = 0.5,
+    max_new_tokens: int = 16000,
+    top_p: float = 1.0,
+    top_k: int = 15,
+    penalty: float = 0.9,
+):
+    print(f'message: {message}')
+    print(f'history: {history}')
+
+    conversation = [
+        {"role": "system", "content": system_prompt}
+    ]
+    for prompt, answer in history:
+        conversation.extend([
+            {"role": "user", "content": prompt},
+            {"role": "assistant", "content": answer},
+        ])
+
+    conversation.append({"role": "user", "content": message})
+
+    input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, return_tensors="pt").to(model.device)
+
+    streamer = TextIteratorStreamer(tokenizer, timeout=60.0, skip_prompt=True, skip_special_tokens=True)
+
+    generate_kwargs = dict(
+        input_ids=input_ids,
+        max_new_tokens = max_new_tokens,
+        do_sample = False if temperature == 0 else True,
+        top_p = top_p,
+        top_k = top_k,
+        temperature = temperature,
+        eos_token_id=[128001,128008,128009],
+        streamer=streamer,
+    )
 # Constants
 INPUT_DIRECTORY = 'input'
 OUTPUT_DIRECTORY = 'output'