Spaces:
Runtime error
Runtime error
File size: 2,365 Bytes
e90622e ec0bc03 e90622e ec0bc03 e90622e ec0bc03 e90622e ec0bc03 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 |
from transformers import AutoModelForCausalLM, AutoTokenizer, Trainer, TrainingArguments
from datasets import load_dataset
import gradio as gr
import torch
# Cargar el modelo y el tokenizador
tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
# Cargar tu conjunto de datos
dataset = load_dataset('csv', data_files='alpaca.csv')
# Preprocesar los datos
def preprocess_function(examples):
inputs = [ex for ex in examples['input_text']]
outputs = [ex for ex in examples['response_text']]
model_inputs = tokenizer(inputs, max_length=512, truncation=True)
# Configurar las etiquetas
with tokenizer.as_target_tokenizer():
labels = tokenizer(outputs, max_length=512, truncation=True)
model_inputs["labels"] = labels["input_ids"]
return model_inputs
tokenized_dataset = dataset.map(preprocess_function, batched=True)
# Configurar los argumentos de entrenamiento
training_args = TrainingArguments(
output_dir="./results",
evaluation_strategy="epoch",
learning_rate=2e-5,
per_device_train_batch_size=2,
num_train_epochs=3,
)
# Crear el Trainer
trainer = Trainer(
model=model,
args=training_args,
train_dataset=tokenized_dataset['train'],
)
# Entrenar el modelo
trainer.train()
# Guardar el modelo entrenado
model.save_pretrained("./mi_modelo_entrenado")
tokenizer.save_pretrained("./mi_modelo_entrenado")
# Cargar el modelo entrenado
model = AutoModelForCausalLM.from_pretrained("./mi_modelo_entrenado")
tokenizer = AutoTokenizer.from_pretrained("./mi_modelo_entrenado")
# Inicializar el historial de conversación
chat_history_ids = None
# Función de chat
def chat_with_bot(user_input):
global chat_history_ids
new_user_input_ids = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors='pt')
bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if chat_history_ids is not None else new_user_input_ids
chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
return tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
# Crear la interfaz de Gradio
iface = gr.Interface(fn=chat_with_bot, inputs="text", outputs="text", title="Chatbot Entrenado")
iface.launch()
|