File size: 2,817 Bytes
9cb6afd |
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 64 65 66 67 68 69 70 71 72 73 74 75 76 77 |
# Copyright (c) Meta Platforms, Inc. and affiliates.
# This software may be used and distributed according to the terms of the GNU General Public License version 3.
from typing import List
import torch
from llama.tokenizer import Tokenizer
from llama.model import Transformer
class LLaMA:
def __init__(self, model: Transformer, tokenizer: Tokenizer):
self.model = model
self.tokenizer = tokenizer
def generate(
self,
prompts: List[str],
max_gen_len: int,
temperature: float = 0.8,
top_p: float = 0.95,
) -> List[str]:
bsz = len(prompts)
params = self.model.params
assert bsz <= params.max_batch_size, (bsz, params.max_batch_size)
prompt_tokens = [self.tokenizer.encode(x, bos=True, eos=False) for x in prompts]
min_prompt_size = min([len(t) for t in prompt_tokens])
max_prompt_size = max([len(t) for t in prompt_tokens])
total_len = min(params.max_seq_len, max_gen_len + max_prompt_size)
tokens = torch.full((bsz, total_len), self.tokenizer.pad_id).cuda().long()
for k, t in enumerate(prompt_tokens):
tokens[k, : len(t)] = torch.tensor(t).long()
input_text_mask = tokens != self.tokenizer.pad_id
start_pos = min_prompt_size
prev_pos = 0
for cur_pos in range(start_pos, total_len):
logits = self.model.forward(tokens[:, prev_pos:cur_pos], prev_pos)
if temperature > 0:
probs = torch.softmax(logits / temperature, dim=-1)
next_token = sample_top_p(probs, top_p)
else:
next_token = torch.argmax(logits, dim=-1)
next_token = next_token.reshape(-1)
# only replace token if prompt has already been generated
next_token = torch.where(
input_text_mask[:, cur_pos], tokens[:, cur_pos], next_token
)
tokens[:, cur_pos] = next_token
prev_pos = cur_pos
decoded = []
for i, t in enumerate(tokens.tolist()):
# cut to max gen len
t = t[: len(prompt_tokens[i]) + max_gen_len]
# cut to eos tok if any
try:
t = t[: t.index(self.tokenizer.eos_id)]
except ValueError:
pass
decoded.append(self.tokenizer.decode(t))
return decoded
def sample_top_p(probs, p):
probs_sort, probs_idx = torch.sort(probs, dim=-1, descending=True)
probs_sum = torch.cumsum(probs_sort, dim=-1)
mask = probs_sum - probs_sort > p
probs_sort[mask] = 0.0
probs_sort.div_(probs_sort.sum(dim=-1, keepdim=True))
next_token = torch.multinomial(probs_sort, num_samples=1)
next_token = torch.gather(probs_idx, -1, next_token)
return next_token |