Download toolformer pytorch - download do código-fonte toolformer pytorch

toolformer pytorch

Código-Fonte de IA

0.0.30

Baixar

Toolformer-Pytorch (wip)

Implementação de Toolformer, modelos de linguagem que podem usar ferramentas, por MetaAI

Apreciação

Stability.ai pelo generoso patrocínio ao trabalho e pesquisa de ponta em inteligência artificial de código aberto
Enrico por dar o pontapé inicial com o commit inicial de diferentes ferramentas!
Agradecemos ao ChatGPT por fazer todas as expressões regulares neste repositório para analisar as funções e parâmetros para as chamadas de API. Eu sou péssimo com expressões regulares, então isso foi uma grande ajuda da IA (sem problemas, foi perfeito).

Instalar

$ pip install toolformer-pytorch

Uso

Exemplo de uso para dar aos modelos de linguagem conhecimento da data e hora atuais.

 import torch
from toolformer_pytorch import Toolformer , PaLM

# simple calendar api call - function that returns a string

def Calendar ():
    import datetime
    from calendar import day_name , month_name
    now = datetime . datetime . now ()
    return f'Today is { day_name [ now . weekday ()] } , { month_name [ now . month ] } { now . day } , { now . year } .'

# prompt for teaching it to use the Calendar function from above

prompt = f"""
Your task is to add calls to a Calendar API to a piece of text.
The API calls should help you get information required to complete the text.
You can call the API by writing "[Calendar()]"
Here are some examples of API calls:
Input: Today is the first Friday of the year.
Output: Today is the first [Calendar()] Friday of the year.
Input: The president of the United States is Joe Biden.
Output: The president of the United States is [Calendar()] Joe Biden.
Input: [input]
Output: 
"""

data = [
    "The store is never open on the weekend, so today it is closed." ,
    "The number of days from now until Christmas is 30" ,
    "The current day of the week is Wednesday."
]

# model - here using PaLM, but any nn.Module that returns logits in the shape (batch, seq, num_tokens) is fine

model = PaLM (
    dim = 512 ,
    depth = 2 ,
    heads = 8 ,
    dim_head = 64
). cuda ()

# toolformer

toolformer = Toolformer (
    model = model ,
    model_seq_len = 256 ,
    teach_tool_prompt = prompt ,
    tool_id = 'Calendar' ,
    tool = Calendar ,
    finetune = True
)

# invoking this will
# (1) prompt the model with your inputs (data), inserted into [input] tag
# (2) with the sampled outputs, filter out the ones that made proper API calls
# (3) execute the API calls with the `tool` given
# (4) filter with the specialized filter function (which can be used independently as shown in the next section)
# (5) fine-tune on the filtered results

filtered_stats = toolformer ( data )

# then, once you see the 'finetune complete' message

response = toolformer . sample_model_with_api_calls ( "How many days until the next new years?" )

# hopefully you see it invoke the calendar and utilize the response of the api call...

A principal novidade do artigo é definir uma pontuação de fitness para as saídas de um transformador instruído a inserir chamadas de API. A pontuação é usada para filtrar as saídas amostradas para ajustar o transformador para fazer chamadas de API que diminuam a perplexidade do texto que o segue.

 import torch

from toolformer_pytorch import (
    Toolformer ,
    PaLM ,
    filter_tokens_with_api_response
)

# model

palm = PaLM (
    dim = 512 ,
    num_tokens = 20000 ,
    depth = 2 ,
    heads = 8 ,
    dim_head = 64
). cuda ()

# mock some tokens

mock_start_pos = 512
mock_api_call_length = 10
mock_api_start_id = 19998
mock_api_stop_id = 19999

tokens = torch . randint ( 0 , 20000 , ( 10 , 1024 )). cuda ()
tokens_with_api_response = torch . randint ( 0 , 20000 , ( 10 , 1024 )). cuda ()
tokens_without_api_response = torch . randint ( 0 , 20000 , ( 10 , 1024 )). cuda ()

tokens_with_api_response [:, mock_start_pos ] = mock_api_start_id
tokens_with_api_response [:, mock_start_pos + mock_api_call_length ] = mock_api_stop_id

tokens_without_api_response [:, mock_start_pos ] = mock_api_start_id
tokens_without_api_response [:, mock_start_pos + mock_api_call_length ] = mock_api_stop_id

# filter

filtered_results = filter_tokens_with_api_response (
    model = palm ,
    tokens = tokens ,
    tokens_with_api_response = tokens_with_api_response ,
    tokens_without_api_response = tokens_without_api_response ,
    filter_threshold = 1. ,
    api_start_token_id = mock_api_start_id ,
    api_end_token_id = mock_api_stop_id
)

Para invocar as ferramentas em uma string gerada pelo modelo de linguagem, use invoke_tools

 from toolformer_pytorch import invoke_tools

def inc ( i ):
    return i + 1

def dec ( i ):
    return i - 1

function_registry = dict (
    inc = inc ,
    dec = dec
)

text = 'make the following api calls: [inc(1)] and [dec(2)] and [ignored(3)]'

invoke_tools ( function_registry , text )

# make the following api calls: [inc(1) → 2] and [dec(2) → 1] and [ignored(3)]

Pendência

Citações

 @inproceedings { Schick2023ToolformerLM ,
    title   = { Toolformer: Language Models Can Teach Themselves to Use Tools } ,
    author  = { Timo Schick and Jane Dwivedi-Yu and Roberto Dessi and Roberta Raileanu and Maria Lomeli and Luke Zettlemoyer and Nicola Cancedda and Thomas Scialom } ,
    year    = { 2023 }
}

 @article { Gao2022PALPL ,
    title   = { PAL: Program-aided Language Models } ,
    author  = { Luyu Gao and Aman Madaan and Shuyan Zhou and Uri Alon and Pengfei Liu and Yiming Yang and Jamie Callan and Graham Neubig } ,
    journal = { ArXiv } ,
    year    = { 2022 } ,
    volume  = { abs/2211.10435 }
}