thomwolf

def top_k_top_p_filtering(logits, top_k=0, top_p=0.0, filter_value=-float('Inf')):
    """ Filter a distribution of logits using top-k and/or nucleus (top-p) filtering
        Args:
            logits: logits distribution shape (vocabulary size)
            top_k >0: keep only top k tokens with highest probability (top-k filtering).
            top_p >0.0: keep the top tokens with cumulative probability >= top_p (nucleus filtering).
                Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751)
    """
    assert logits.dim() == 1  # batch size 1 for now - could be updated for more but the code would be less clear
    top_k = min(top_k, logits.size(-1))  # Safety check

movefast

class Seq2SeqAttnRNN(nn.Module):
    def __init__(self, vecs_enc, itos_enc, em_sz_enc, vecs_dec, itos_dec, em_sz_dec, nh, out_sl, nl=2):
        super().__init__()
        self.emb_enc = create_emb(vecs_enc, itos_enc, em_sz_enc)
        self.nl,self.nh,self.out_sl = nl,nh,out_sl
        self.gru_enc = nn.GRU(em_sz_enc, nh, num_layers=nl, dropout=0.25)
        self.out_enc = nn.Linear(nh, em_sz_dec, bias=False)
        self.emb_dec = create_emb(vecs_dec, itos_dec, em_sz_dec)
        self.gru_dec = nn.GRU(em_sz_dec, em_sz_dec, num_layers=nl, dropout=0.1)
        self.emb_enc_drop = nn.Dropout(0.15)

BrikerMan

from gensim.models import KeyedVectors

# Load gensim word2vec
w2v_path = '<Gensim File Path>'
w2v = KeyedVectors.load_word2vec_format(w2v_path)

import io

# Vector file, `\t` seperated the vectors and `\n` seperate the words
"""