testing

app.py

@@ -50,25 +50,20 @@ def generate(
         input_ids = input_ids[-MAX_INPUT_TOKEN_LENGTH:]
         gr.Warning("Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
 
-    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
-    generate_kwargs = dict(
-        {"input_ids": input_ids},
-        streamer=streamer,
-        max_new_tokens=max_new_tokens,
-        do_sample=True,
-        top_p=top_p,
-        top_k=top_k,
-        temperature=temperature,
-        num_beams=1,
-        repetition_penalty=repetition_penalty,
-    )
-    t = Thread(target=model.generate, kwargs=generate_kwargs)
-    t.start()
-
-    outputs = []
-    for text in streamer:
-        outputs.append(text)
-        yield "".join(outputs)
+    input_ids = tokenizer(current_input, return_tensors="pt").to("cuda")
+
+    # Generate 
+    output_ids = model.generate(input_ids=input_ids,
+                              max_new_tokens=max_new_tokens, 
+                              do_sample=True,
+                              top_p=top_p,
+                              top_k=top_k,
+                              temperature=temperature,
+                              repetition_penalty=repetition_penalty)
+
+    # Stream output    
+    for id in output_ids.tolist()[0]:
+     yield tokenizer.decode(id)
 
 
 chat_interface = gr.ChatInterface(