File size: 2,933 Bytes
13362e2 |
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 |
# Copyright 2024 the LlamaFactory team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import math
from contextlib import nullcontext
from typing import TYPE_CHECKING
import torch
from transformers.integrations import is_deepspeed_zero3_enabled
from ...extras.logging import get_logger
if TYPE_CHECKING:
from transformers import PreTrainedModel, PreTrainedTokenizer
logger = get_logger(__name__)
def _noisy_mean_initialization(embed_weight: "torch.Tensor", num_new_tokens: int) -> None:
embedding_dim = embed_weight.size(1)
avg_weight = embed_weight[:-num_new_tokens].mean(dim=0, keepdim=True)
noise_weight = torch.empty_like(embed_weight[-num_new_tokens:])
noise_weight.normal_(mean=0, std=(1.0 / math.sqrt(embedding_dim)))
embed_weight[-num_new_tokens:] = avg_weight + noise_weight
def resize_embedding_layer(model: "PreTrainedModel", tokenizer: "PreTrainedTokenizer") -> None:
r"""
Resize token embeddings.
"""
if is_deepspeed_zero3_enabled():
import deepspeed # type: ignore
params = [model.get_input_embeddings().weight]
if model.get_output_embeddings() is not None and not model.config.tie_word_embeddings:
params.append(model.get_output_embeddings().weight)
context_maybe_zero3 = deepspeed.zero.GatheredParameters(params, modifier_rank=0)
else:
context_maybe_zero3 = nullcontext()
with context_maybe_zero3:
current_embedding_size = model.get_input_embeddings().weight.size(0)
if len(tokenizer) > current_embedding_size:
if getattr(model, "quantization_method", None):
raise ValueError("Cannot resize embedding layers of a quantized model.")
if not isinstance(model.get_output_embeddings(), torch.nn.Linear):
raise ValueError("Current model does not support resizing embedding layers.")
model.resize_token_embeddings(len(tokenizer), pad_to_multiple_of=64)
with context_maybe_zero3:
new_embedding_size = model.get_input_embeddings().weight.size(0)
num_new_tokens = new_embedding_size - current_embedding_size
_noisy_mean_initialization(model.get_input_embeddings().weight.data, num_new_tokens)
_noisy_mean_initialization(model.get_output_embeddings().weight.data, num_new_tokens)
logger.info("Resized token embeddings from {} to {}.".format(current_embedding_size, new_embedding_size))
|