File size: 3,102 Bytes
b971d47
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import torch
import torch.nn.functional as F

def top_k_top_p_filtering(
    logits, top_k=0, top_p=1.0, filter_value=-float("Inf"), min_tokens_to_keep=1
):
    """Filter a distribution of logits using top-k and/or nucleus (top-p) filtering
    Args:
        logits: logits distribution shape (batch size, vocabulary size)
        if top_k > 0: keep only top k tokens with highest probability (top-k filtering).
        if top_p < 1.0: 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)
        Make sure we keep at least min_tokens_to_keep per batch example in the output
    From: https://gist.github.com/thomwolf/1a5a29f6962089e871b94cbd09daf317
    """
    if top_k > 0:
        top_k = min(
            max(top_k, min_tokens_to_keep), logits.size(-1)
        )  # Safety check
        # Remove all tokens with a probability less than the last token of the top-k
        indices_to_remove = logits < torch.topk(logits, top_k)[0][..., -1, None]
        logits[indices_to_remove] = filter_value

    if top_p < 1.0:
        sorted_logits, sorted_indices = torch.sort(logits, descending=True)
        cumulative_probs = torch.cumsum(
            F.softmax(sorted_logits, dim=-1), dim=-1
        )

        # Remove tokens with cumulative probability above the threshold (token with 0 are kept)
        sorted_indices_to_remove = cumulative_probs > top_p
        if min_tokens_to_keep > 1:
            # Keep at least min_tokens_to_keep (set to min_tokens_to_keep-1 because we add the first one below)
            sorted_indices_to_remove[..., :min_tokens_to_keep] = 0
        # Shift the indices to the right to keep also the first token above the threshold
        sorted_indices_to_remove[..., 1:] = sorted_indices_to_remove[
            ..., :-1
        ].clone()
        sorted_indices_to_remove[..., 0] = 0

        # scatter sorted tensors to original indexing
        indices_to_remove = sorted_indices_to_remove.scatter(
            1, sorted_indices, sorted_indices_to_remove
        )
        logits[indices_to_remove] = filter_value
    return logits
    
def topk_sampling(logits, top_k=10, top_p=1.0, temperature=1.0):
    # temperature: (`optional`) float
    #     The value used to module the next token probabilities. Must be strictly positive. Default to 1.0.
    # top_k: (`optional`) int
    #     The number of highest probability vocabulary tokens to keep for top-k-filtering. Between 1 and infinity. Default to 50.
    # top_p: (`optional`) float
    #     The cumulative probability of parameter highest probability vocabulary tokens to keep for nucleus sampling. Must be between 0 and 1. Default to 1.

    # Temperature (higher temperature => more likely to sample low probability tokens)
    if temperature != 1.0:
        logits = logits / temperature
    # Top-p/top-k filtering
    logits = top_k_top_p_filtering(logits, top_k=top_k, top_p=top_p)
    # Sample
    token = torch.multinomial(F.softmax(logits, dim=-1), num_samples=1)
    return token