Update app.py

app.py

@@ -211,85 +211,6 @@ async def train_model_async(progress=gr.Progress(track_tqdm=True)):
     except Exception as e:
         raise gr.Error(e)
 
-DEFAULT_SYSTEM_PROMPT = "あなたは誠実で優秀な日本人のアシスタントです。特に指示が無い場合は、常に日本語で回答してください。"
-memory = [{"role": "system", "content": DEFAULT_SYSTEM_PROMPT}]
-
-def reset_memory():
-    global memory
-    memory = [{"role": "system", "content": DEFAULT_SYSTEM_PROMPT}]
-    return None
-
-def init():
-    try:
-        global llamaTokenizer, llamaModel
-        llamaTokenizer = AutoTokenizer.from_pretrained("elyza/Llama-3-ELYZA-JP-8B", trust_remote_code=True)
-        llamaModel = AutoModelForCausalLM.from_pretrained(
-            "elyza/Llama-3-ELYZA-JP-8B",
-            torch_dtype="auto",
-            device_map="auto",
-        )
-        llamaModel.eval()
-
-        return [gr.Button(visible=False), gr.Textbox(visible=True), gr.Button(visible=True)]    
-    except Exception as e:
-        raise gr.Error(e)
-
-async def chat(message):
-    try:
-        async with Translator() as translator:
-            translated_input = await translator.translate(message, dest="ja")
-            jp_input = translated_input.text
-            output_language = translated_input.src
-
-            global memory
-
-            memory.append({"role": "user", "content": jp_input})
-
-            prompt = llamaTokenizer.apply_chat_template(
-                memory,
-                tokenize=False,
-                add_generation_prompt=True
-            )
-
-            token_ids = llamaTokenizer.encode(
-                prompt, add_special_tokens=False, return_tensors="pt"
-            )
-
-            with torch.no_grad():
-                output_ids = llamaModel.generate(
-                    token_ids.to(llamaModel.device),
-                    max_new_tokens=1024,
-                    do_sample=True,
-                    temperature=0.6,
-                    top_p=0.9,
-                )
-
-            output = llamaTokenizer.decode(
-                output_ids.tolist()[0][token_ids.size(1):], skip_special_tokens=True
-            )
-
-            memory.append({"role": "assistant", "content": output})
-
-            translated_output = await translator.translate(output, dest=output_language)
-
-            if os.path.exists(f"./VRM-Emotions/model.safetensors"):
-                newTokenizer = AutoTokenizer.from_pretrained("./VRM-Emotions", trust_remote_code=True)
-                newConfig = AutoConfig.from_pretrained("./VRM-Emotions")
-                newModel = AutoModelForSequenceClassification.from_pretrained("./VRM-Emotions", config=newConfig)
-
-                sentence = newTokenizer(output, return_tensors="pt", padding=True, truncation=True, max_length=512)
-                with torch.no_grad():
-                    outputs = newModel(**sentence)
-                    logits = outputs.logits
-                    predicted = torch.argmax(logits, dim=-1).item()
-                    label = newModel.config.id2label[predicted]
-
-                return "[" + label + "] " + translated_output.text
-            else:
-                return translated_output.text
-    except Exception as e:
-        raise gr.Error(e)
-
 with gr.Blocks() as demo:
     with gr.Tab("Prepare Dataset"):
         dataset_files = gr.Files(label="CSV Files")
@@ -302,24 +223,4 @@ with gr.Blocks() as demo:
         train_btn = gr.Button("Train All")
         train_btn.click(train_model_async, inputs=None, outputs=[train_results, models_files])
 
-    with gr.Tab("Testing"):
-        chatbot = gr.Chatbot(type="messages")
-        start = gr.Button("Start")
-        msg = gr.Textbox(visible=False)
-        clear = gr.Button("Clear", visible=False)
-
-        async def user(history, message):
-            return history + [{"role": "user", "content": message}], ""
-
-        async def llm(history):
-            message = next(
-                (entry["content"] for entry in reversed(history) if entry["role"] == "user"), None
-            )
-            response = await chat(message)
-            return history + [{"role": "assistant", "content": response}]
-
-        start.click(init, None, [start, msg, clear])
-        msg.submit(user, [chatbot, msg], [chatbot, msg], queue=False).then(llm, chatbot, chatbot)
-        clear.click(reset_memory, None, chatbot, queue=False)
-
 demo.launch()