convmodel

convmodel

convmodel fornece um modelo de conversação baseado no modelo GPT-2 de transformadores

Características

• Utiliza o modelo GPT2 para gerar resposta
• Lida com conversas em várias voltas
• Fornece interfaces úteis para ajustar o modelo e gerar uma resposta a partir de um determinado contexto

Um exemplo simples de ajuste fino do modelo GPT-2 e geração de uma resposta:

convmodel import ConversationModel from convmodel import ConversationExample # Load model on GPU model = ConversationModel.from_pretrained("gpt2") # Define training/validation examples train_iterator = [ ConversationExample(conversation=[ "Hello", "Hi, how are you?", "Good, thank you, how about you?", "Good, thanks!" ]), ConversationExample(conversation=[ "I am hungry", "How about eating pizza?" ]), ] valid_iterator = [ ConversationExample(conversation=[ "Tired...", "Let's have a break!", "Nice idea!" ]), ] # Fine-tune model model.fit(train_iterator=train_iterator, valid_iterator=valid_iterator) # Generate response model.generate(context=["Hello", "How are you"], do_sample=True, top_p=0.95, top_k=50) # Output could be like below if sufficient examples were given. # => ConversationModelOutput(responses=['Good thank you'], context=['Hello', 'How are you'])">

 from convmodel import ConversationModel
from convmodel import ConversationExample

# Load model on GPU
model = ConversationModel . from_pretrained ( "gpt2" )

# Define training/validation examples
train_iterator = [
    ConversationExample ( conversation = [
        "Hello" ,
        "Hi, how are you?" ,
        "Good, thank you, how about you?" ,
        "Good, thanks!"
    ]),
    ConversationExample ( conversation = [
        "I am hungry" ,
        "How about eating pizza?"
    ]),
]
valid_iterator = [
    ConversationExample ( conversation = [
        "Tired..." ,
        "Let's have a break!" ,
        "Nice idea!"
    ]),
]

# Fine-tune model
model . fit ( train_iterator = train_iterator , valid_iterator = valid_iterator )

# Generate response
model . generate ( context = [ "Hello" , "How are you" ], do_sample = True , top_p = 0.95 , top_k = 50 )
# Output could be like below if sufficient examples were given.
# => ConversationModelOutput(responses=['Good thank you'], context=['Hello', 'How are you'])

Consulte o documento para obter mais detalhes sobre instalação, arquitetura do modelo e uso.

• Instalar
• Visão geral da arquitetura do modelo
• Treinamento de modelo
• Geração de Resposta
• CLI (Experimental)

Divirta-se conversando com sua IA conversacional