Update app.py

app.py

@@ -1,15 +1,19 @@
+import os
 import threading
 import time
 import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer
 import torch
 
+hf_token = os.getenv("Key")
+
 # Configuração do modelo
 model_id = "lxcorp/Synap-2b"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(model_id, token=hf_token)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
-    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32
+    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+    token=hf_token
 )
 device = "cuda" if torch.cuda.is_available() else "cpu"
 model.to(device)
@@ -44,7 +48,7 @@ def generate_response(message, max_tokens, temperature, top_p):
     global stop_signal
     stop_signal = False
 
-    prompt = f"Question: {message}\nThinking: \nAnswer:"
+    prompt = f"Entrada: {message}\nResposta:"
     inputs = tokenizer(prompt, return_tensors="pt").to(device)
 
     streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
@@ -75,12 +79,12 @@ def generate_response(message, max_tokens, temperature, top_p):
 
 # Interface Gradio
 with gr.Blocks(css=css, theme="NoCrypt/miku") as app:
-    chatbot = gr.Chatbot(label="λ", elem_id="chatbot")
+    chatbot = gr.Chatbot(label="Synap - 2B", elem_id="chatbot")
     msg = gr.Textbox(label="Mensagem", placeholder="Digite aqui...", lines=2)
     send_btn = gr.Button("Enviar")
     stop_btn = gr.Button("Parar")
 
-    max_tokens = gr.Slider(64, 512, value=128, step=1, label="Max Tokens")
+    max_tokens = gr.Slider(64, 1024, value=128, step=1, label="Max Tokens")
     temperature = gr.Slider(0.1, 1.5, value=0.7, step=0.1, label="Temperature")
     top_p = gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p")