manueldeprada

#!/usr/bin/python3

import re
import signal
import dbus
from gi.repository import GLib
from dbus.mainloop.glib import DBusGMainLoop

import gi
gi.require_version('Gst', '1.0')

manueldeprada

First, it is you need to create a conda or venv environment. This mamba.yml file contains the packages:

name: QAFactEval
channels:
- conda-forge
dependencies:
- python=3.8.18=hd12c33a_0_cpython
- spacy=2.2.4 
- spacy-model-en_core_web_sm=2.2.5

manueldeprada

from decoders import inject_supervitamined_decoders, StochasticBeamSearchDecoder, FakeTransformer
from transformers import T5ForConditionalGeneration, T5Tokenizer
import torch


# pip install decoders

# this demonstration uses a fake toy transformer (https://manueldeprada.com/blog/posts/toy-probabilistic-transformer/)
# to test the correctness of the stochastic beam search implementation
def test_fake_transformer():

manueldeprada

from transformers import PreTrainedModel, PretrainedConfig, PreTrainedTokenizer, BatchEncoding
from transformers.modeling_outputs import Seq2SeqLMOutput
import torch


class FakeTransformerConfig(PretrainedConfig):
    model_type = "FakeTransformer"

    def __init__(self, vocab_size=4, **kwargs):
        super().__init__(pad_token_id=-1, eos_token_id=3, bos_token_id=0, **kwargs)