test

app.py

@@ -8,6 +8,14 @@ model_name = "lmsys/vicuna-7b-v1.3"
 model = AutoModelForCausalLM.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
+def respond_vicuna(message, chat_history, vicuna_chatbot):
+    input_ids = tokenizer.encode(message, return_tensors="pt")
+    output = model.generate(input_ids, max_length=50, num_beams=5, no_repeat_ngram_size=2)
+    bot_message = tokenizer.decode(output[0], skip_special_tokens=True)
+    chat_history.append((message, bot_message))
+    time.sleep(2)
+    return "", chat_history
+
 with gr.Blocks() as demo:
     gr.Markdown("# LLM Evaluator With Linguistic Scrutiny")
 
@@ -60,6 +68,7 @@ with gr.Blocks() as demo:
         time.sleep(2)
         return "", chat_history
 
-    prompt.submit(respond, [prompt, vicuna_chatbot1, vicuna_chatbot1_chunk])
+    # Replace the old respond function with the new general function for Vicuna
+    prompt.submit(lambda message, chat_history: respond_vicuna(message, chat_history, vicuna_chatbot1), [prompt, vicuna_chatbot1, vicuna_chatbot1_chunk])
 
 demo.launch()