Merge pull request #169 from NanoCode012/feat/landmark
Browse files- README.md +2 -0
- src/axolotl/monkeypatch/llama_landmark_attn.py +1595 -0
- src/axolotl/utils/models.py +20 -8
- src/axolotl/utils/trainer.py +18 -0
README.md
CHANGED
@@ -417,6 +417,8 @@ flash_attention: # require a100 for llama
|
|
417 |
# whether to use scaled-dot-product attention
|
418 |
# https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html
|
419 |
sdp_attention:
|
|
|
|
|
420 |
|
421 |
# resume from a specific checkpoint dir
|
422 |
resume_from_checkpoint:
|
|
|
417 |
# whether to use scaled-dot-product attention
|
418 |
# https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html
|
419 |
sdp_attention:
|
420 |
+
# Landmark attention (only llama)
|
421 |
+
landmark_attention:
|
422 |
|
423 |
# resume from a specific checkpoint dir
|
424 |
resume_from_checkpoint:
|
src/axolotl/monkeypatch/llama_landmark_attn.py
ADDED
@@ -0,0 +1,1595 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# pylint: skip-file
|
2 |
+
# coding=utf-8
|
3 |
+
# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
|
4 |
+
#
|
5 |
+
# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
|
6 |
+
# and OPT implementations in this library. It has been modified from its
|
7 |
+
# original forms to accommodate minor architectural differences compared
|
8 |
+
# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
|
9 |
+
#
|
10 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
11 |
+
# you may not use this file except in compliance with the License.
|
12 |
+
# You may obtain a copy of the License at
|
13 |
+
#
|
14 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
15 |
+
#
|
16 |
+
# Unless required by applicable law or agreed to in writing, software
|
17 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
18 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
19 |
+
# See the License for the specific language governing permissions and
|
20 |
+
# limitations under the License.
|
21 |
+
"""
|
22 |
+
PyTorch LLaMA model.
|
23 |
+
Taken from https://github.com/epfml/landmark-attention/blob/main/llama/llama_mem.py and modified.
|
24 |
+
"""
|
25 |
+
import math
|
26 |
+
from typing import List, Optional, Tuple, Union
|
27 |
+
|
28 |
+
import torch
|
29 |
+
import torch.utils.checkpoint
|
30 |
+
from torch import nn
|
31 |
+
from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
|
32 |
+
from transformers.activations import ACT2FN
|
33 |
+
from transformers.modeling_outputs import (
|
34 |
+
BaseModelOutputWithPast,
|
35 |
+
CausalLMOutputWithPast,
|
36 |
+
SequenceClassifierOutputWithPast,
|
37 |
+
)
|
38 |
+
from transformers.modeling_utils import PreTrainedModel
|
39 |
+
from transformers.models.llama.configuration_llama import LlamaConfig
|
40 |
+
from transformers.utils import (
|
41 |
+
add_start_docstrings,
|
42 |
+
add_start_docstrings_to_model_forward,
|
43 |
+
logging,
|
44 |
+
replace_return_docstrings,
|
45 |
+
)
|
46 |
+
|
47 |
+
logger = logging.get_logger(__name__)
|
48 |
+
|
49 |
+
_CONFIG_FOR_DOC = "LlamaConfig"
|
50 |
+
|
51 |
+
MEM_TOKEN = "<landmark>" # nosec
|
52 |
+
|
53 |
+
|
54 |
+
# Copied from transformers.models.bart.modeling_bart._make_causal_mask
|
55 |
+
def _make_causal_mask(
|
56 |
+
input_ids_shape: torch.Size,
|
57 |
+
dtype: torch.dtype,
|
58 |
+
device: torch.device,
|
59 |
+
past_key_values_length: int = 0,
|
60 |
+
):
|
61 |
+
"""
|
62 |
+
Make causal mask used for bi-directional self-attention.
|
63 |
+
"""
|
64 |
+
bsz, tgt_len = input_ids_shape
|
65 |
+
mask = torch.full(
|
66 |
+
(tgt_len, tgt_len),
|
67 |
+
torch.tensor(torch.finfo(dtype).min, device=device),
|
68 |
+
device=device,
|
69 |
+
)
|
70 |
+
mask_cond = torch.arange(mask.size(-1), device=device)
|
71 |
+
mask.masked_fill_(mask_cond < (mask_cond + 1).view(mask.size(-1), 1), 0)
|
72 |
+
mask = mask.to(dtype)
|
73 |
+
|
74 |
+
if past_key_values_length > 0:
|
75 |
+
mask = torch.cat(
|
76 |
+
[
|
77 |
+
torch.zeros(
|
78 |
+
tgt_len, past_key_values_length, dtype=dtype, device=device
|
79 |
+
),
|
80 |
+
mask,
|
81 |
+
],
|
82 |
+
dim=-1,
|
83 |
+
)
|
84 |
+
return mask[None, None, :, :].expand(
|
85 |
+
bsz, 1, tgt_len, tgt_len + past_key_values_length
|
86 |
+
)
|
87 |
+
|
88 |
+
|
89 |
+
# Copied from transformers.models.bart.modeling_bart._expand_mask
|
90 |
+
def _expand_mask(mask: torch.Tensor, dtype: torch.dtype, tgt_len: Optional[int] = None):
|
91 |
+
"""
|
92 |
+
Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.
|
93 |
+
"""
|
94 |
+
bsz, src_len = mask.size()
|
95 |
+
tgt_len = tgt_len if tgt_len is not None else src_len
|
96 |
+
|
97 |
+
expanded_mask = mask[:, None, None, :].expand(bsz, 1, tgt_len, src_len).to(dtype)
|
98 |
+
|
99 |
+
inverted_mask = 1.0 - expanded_mask
|
100 |
+
|
101 |
+
return inverted_mask.masked_fill(
|
102 |
+
inverted_mask.to(torch.bool), torch.finfo(dtype).min
|
103 |
+
)
|
104 |
+
|
105 |
+
|
106 |
+
class LlamaRMSNorm(nn.Module):
|
107 |
+
def __init__(self, hidden_size, eps=1e-6):
|
108 |
+
"""
|
109 |
+
LlamaRMSNorm is equivalent to T5LayerNorm
|
110 |
+
"""
|
111 |
+
super().__init__()
|
112 |
+
self.weight = nn.Parameter(torch.ones(hidden_size))
|
113 |
+
self.variance_epsilon = eps
|
114 |
+
|
115 |
+
def forward(self, hidden_states):
|
116 |
+
variance = hidden_states.to(torch.float32).pow(2).mean(-1, keepdim=True)
|
117 |
+
hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon)
|
118 |
+
|
119 |
+
# convert into half-precision if necessary
|
120 |
+
if self.weight.dtype in [torch.float16, torch.bfloat16]:
|
121 |
+
hidden_states = hidden_states.to(self.weight.dtype)
|
122 |
+
|
123 |
+
return self.weight * hidden_states
|
124 |
+
|
125 |
+
|
126 |
+
class LlamaRotaryEmbedding(torch.nn.Module):
|
127 |
+
def __init__(self, dim, max_position_embeddings=2048, base=10000, device=None):
|
128 |
+
super().__init__()
|
129 |
+
inv_freq = 1.0 / (base ** (torch.arange(0, dim, 2).float().to(device) / dim))
|
130 |
+
self.register_buffer("inv_freq", inv_freq)
|
131 |
+
|
132 |
+
# Build here to make `torch.jit.trace` work.
|
133 |
+
self.max_seq_len_cached = max_position_embeddings
|
134 |
+
t = torch.arange(
|
135 |
+
self.max_seq_len_cached,
|
136 |
+
device=self.inv_freq.device,
|
137 |
+
dtype=self.inv_freq.dtype,
|
138 |
+
)
|
139 |
+
freqs = torch.einsum("i,j->ij", t, self.inv_freq)
|
140 |
+
# Different from paper, but it uses a different permutation in order to obtain the same calculation
|
141 |
+
emb = torch.cat((freqs, freqs), dim=-1)
|
142 |
+
self.register_buffer(
|
143 |
+
"cos_cached", emb.cos()[None, None, :, :], persistent=False
|
144 |
+
)
|
145 |
+
self.register_buffer(
|
146 |
+
"sin_cached", emb.sin()[None, None, :, :], persistent=False
|
147 |
+
)
|
148 |
+
|
149 |
+
def forward(self, x, seq_len=None):
|
150 |
+
# x: [bs, num_attention_heads, seq_len, head_size]
|
151 |
+
# This `if` block is unlikely to be run after we build sin/cos in `__init__`. Keep the logic here just in case.
|
152 |
+
if seq_len > self.max_seq_len_cached:
|
153 |
+
self.max_seq_len_cached = seq_len
|
154 |
+
t = torch.arange(
|
155 |
+
self.max_seq_len_cached, device=x.device, dtype=self.inv_freq.dtype
|
156 |
+
)
|
157 |
+
freqs = torch.einsum("i,j->ij", t, self.inv_freq)
|
158 |
+
# Different from paper, but it uses a different permutation in order to obtain the same calculation
|
159 |
+
emb = torch.cat((freqs, freqs), dim=-1).to(x.device)
|
160 |
+
self.register_buffer(
|
161 |
+
"cos_cached", emb.cos()[None, None, :, :], persistent=False
|
162 |
+
)
|
163 |
+
self.register_buffer(
|
164 |
+
"sin_cached", emb.sin()[None, None, :, :], persistent=False
|
165 |
+
)
|
166 |
+
return (
|
167 |
+
self.cos_cached[:, :, :seq_len, ...].to(dtype=x.dtype),
|
168 |
+
self.sin_cached[:, :, :seq_len, ...].to(dtype=x.dtype),
|
169 |
+
)
|
170 |
+
|
171 |
+
|
172 |
+
def rotate_half(x):
|
173 |
+
"""Rotates half the hidden dims of the input."""
|
174 |
+
x1 = x[..., : x.shape[-1] // 2]
|
175 |
+
x2 = x[..., x.shape[-1] // 2 :]
|
176 |
+
return torch.cat((-x2, x1), dim=-1)
|
177 |
+
|
178 |
+
|
179 |
+
def apply_rotary_pos_emb(q, k, cos, sin, position_ids):
|
180 |
+
# The first two dimensions of cos and sin are always 1, so we can `squeeze` them.
|
181 |
+
cos = cos.squeeze(1).squeeze(0) # [seq_len, dim]
|
182 |
+
sin = sin.squeeze(1).squeeze(0) # [seq_len, dim]
|
183 |
+
cos = cos[position_ids].unsqueeze(1) # [bs, 1, seq_len, dim]
|
184 |
+
sin = sin[position_ids].unsqueeze(1) # [bs, 1, seq_len, dim]
|
185 |
+
if q is None:
|
186 |
+
q_embed = None
|
187 |
+
else:
|
188 |
+
q_embed = (q * cos) + (rotate_half(q) * sin)
|
189 |
+
k_embed = (k * cos) + (rotate_half(k) * sin)
|
190 |
+
return q_embed, k_embed
|
191 |
+
|
192 |
+
|
193 |
+
class LlamaMLP(nn.Module):
|
194 |
+
def __init__(
|
195 |
+
self,
|
196 |
+
hidden_size: int,
|
197 |
+
intermediate_size: int,
|
198 |
+
hidden_act: str,
|
199 |
+
):
|
200 |
+
super().__init__()
|
201 |
+
self.gate_proj = nn.Linear(hidden_size, intermediate_size, bias=False)
|
202 |
+
self.down_proj = nn.Linear(intermediate_size, hidden_size, bias=False)
|
203 |
+
self.up_proj = nn.Linear(hidden_size, intermediate_size, bias=False)
|
204 |
+
self.act_fn = ACT2FN[hidden_act]
|
205 |
+
|
206 |
+
def forward(self, x):
|
207 |
+
return self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x))
|
208 |
+
|
209 |
+
|
210 |
+
class LandmarkGroupedSoftmaxFunction(torch.autograd.Function):
|
211 |
+
# Note that forward, setup_context, and backward are @staticmethods
|
212 |
+
@staticmethod
|
213 |
+
def forward(ctx, x, dim, mem_cnt, resp_mem_idx):
|
214 |
+
new_shape = list(x.shape)
|
215 |
+
new_shape[dim] = mem_cnt # max_mem_cnt.item()
|
216 |
+
max_by_group = x.new_zeros((*new_shape,))
|
217 |
+
max_by_group.scatter_reduce_(
|
218 |
+
src=x, index=resp_mem_idx, dim=dim, reduce="amax", include_self=False
|
219 |
+
)
|
220 |
+
|
221 |
+
maxes = torch.gather(max_by_group, dim, resp_mem_idx)
|
222 |
+
# x_exp = torch.exp(x - torch.where(torch.isinf(maxes), 0, maxes))
|
223 |
+
x_exp = torch.exp((x - maxes).to(torch.float32))
|
224 |
+
|
225 |
+
cumsum_by_group = torch.zeros_like(max_by_group, dtype=x_exp.dtype)
|
226 |
+
|
227 |
+
cumsum_by_group.scatter_add_(
|
228 |
+
dim,
|
229 |
+
resp_mem_idx,
|
230 |
+
x_exp,
|
231 |
+
)
|
232 |
+
denom = torch.gather(cumsum_by_group, dim, resp_mem_idx)
|
233 |
+
|
234 |
+
# probs = torch.where(denom < 0.5, 0, x_exp / denom)
|
235 |
+
probs = x_exp / denom
|
236 |
+
|
237 |
+
ctx.mem_cnt = mem_cnt
|
238 |
+
ctx.dim = dim
|
239 |
+
ctx.save_for_backward(resp_mem_idx, probs)
|
240 |
+
|
241 |
+
return probs
|
242 |
+
|
243 |
+
@staticmethod
|
244 |
+
def backward(ctx, grad_probs):
|
245 |
+
mem_cnt = ctx.mem_cnt
|
246 |
+
dim = ctx.dim
|
247 |
+
resp_mem_idx, probs = ctx.saved_tensors
|
248 |
+
grad_x = grad_dim = grad_mem_cnt = grad_resp_mem_idx = None
|
249 |
+
|
250 |
+
if ctx.needs_input_grad[0] or ctx.needs_input_grad[4]:
|
251 |
+
grad_pair = grad_probs * probs
|
252 |
+
|
253 |
+
new_shape = list(probs.shape)
|
254 |
+
new_shape[dim] = mem_cnt # max_mem_cnt.item()
|
255 |
+
cumsum_by_group = grad_pair.new_zeros((*new_shape,))
|
256 |
+
cumsum_by_group.scatter_add_(dim, resp_mem_idx, grad_pair)
|
257 |
+
|
258 |
+
if ctx.needs_input_grad[0]:
|
259 |
+
grad_sum = torch.gather(cumsum_by_group, dim, resp_mem_idx)
|
260 |
+
grad_x = grad_pair - probs * grad_sum
|
261 |
+
assert not ctx.needs_input_grad[1]
|
262 |
+
assert not ctx.needs_input_grad[2]
|
263 |
+
assert not ctx.needs_input_grad[3]
|
264 |
+
|
265 |
+
return grad_x, grad_dim, grad_mem_cnt, grad_resp_mem_idx
|
266 |
+
|
267 |
+
|
268 |
+
def landmark_grouped_softmax(x, dim, is_mem, last_section_mask):
|
269 |
+
last_and_rest_mask = last_section_mask # | mask
|
270 |
+
|
271 |
+
full_access_mask = is_mem | last_and_rest_mask
|
272 |
+
|
273 |
+
max_mem_cnt = 16
|
274 |
+
mem_group_idx = torch.cumsum(is_mem, dim=dim)
|
275 |
+
mem_bucket_id = max_mem_cnt - 1
|
276 |
+
resp_mem_idx = torch.where(
|
277 |
+
last_and_rest_mask,
|
278 |
+
max_mem_cnt - 1,
|
279 |
+
torch.where(is_mem, mem_bucket_id, mem_group_idx),
|
280 |
+
)
|
281 |
+
probs = LandmarkGroupedSoftmaxFunction.apply(x, dim, max_mem_cnt, resp_mem_idx)
|
282 |
+
|
283 |
+
new_shape = list(x.shape)
|
284 |
+
new_shape[dim] = max_mem_cnt
|
285 |
+
group_prob = probs.new_zeros((*new_shape,))
|
286 |
+
group_prob.scatter_(
|
287 |
+
dim, torch.where(is_mem, mem_group_idx - 1, max_mem_cnt - 1), probs
|
288 |
+
)
|
289 |
+
probs = probs.mul(
|
290 |
+
torch.where(
|
291 |
+
full_access_mask,
|
292 |
+
last_section_mask,
|
293 |
+
torch.gather(group_prob, dim, resp_mem_idx),
|
294 |
+
)
|
295 |
+
)
|
296 |
+
|
297 |
+
return probs
|
298 |
+
|
299 |
+
|
300 |
+
class LlamaAttention(nn.Module):
|
301 |
+
"""Multi-headed attention from 'Attention Is All You Need' paper"""
|
302 |
+
|
303 |
+
def __init__(self, config: LlamaConfig):
|
304 |
+
super().__init__()
|
305 |
+
self.config = config
|
306 |
+
self.hidden_size = config.hidden_size
|
307 |
+
self.num_heads = config.num_attention_heads
|
308 |
+
self.head_dim = self.hidden_size // self.num_heads
|
309 |
+
self.max_position_embeddings = config.max_position_embeddings
|
310 |
+
|
311 |
+
if (self.head_dim * self.num_heads) != self.hidden_size:
|
312 |
+
raise ValueError(
|
313 |
+
f"hidden_size must be divisible by num_heads (got `hidden_size`: {self.hidden_size}"
|
314 |
+
f" and `num_heads`: {self.num_heads})."
|
315 |
+
)
|
316 |
+
self.q_proj = nn.Linear(
|
317 |
+
self.hidden_size, self.num_heads * self.head_dim, bias=False
|
318 |
+
)
|
319 |
+
self.k_proj = nn.Linear(
|
320 |
+
self.hidden_size, self.num_heads * self.head_dim, bias=False
|
321 |
+
)
|
322 |
+
self.v_proj = nn.Linear(
|
323 |
+
self.hidden_size, self.num_heads * self.head_dim, bias=False
|
324 |
+
)
|
325 |
+
self.o_proj = nn.Linear(
|
326 |
+
self.num_heads * self.head_dim, self.hidden_size, bias=False
|
327 |
+
)
|
328 |
+
self.rotary_emb = LlamaRotaryEmbedding(
|
329 |
+
self.head_dim, max_position_embeddings=self.max_position_embeddings
|
330 |
+
)
|
331 |
+
|
332 |
+
self.mem_freq = None
|
333 |
+
self.top_k = None
|
334 |
+
self.max_cache_size = None
|
335 |
+
|
336 |
+
def _shape(self, tensor: torch.Tensor, seq_len: int, bsz: int):
|
337 |
+
return (
|
338 |
+
tensor.view(bsz, seq_len, self.num_heads, self.head_dim)
|
339 |
+
.transpose(1, 2)
|
340 |
+
.contiguous()
|
341 |
+
)
|
342 |
+
|
343 |
+
def set_mem_cache_args(self, mem_freq, top_k, max_cache_size):
|
344 |
+
self.mem_freq = mem_freq
|
345 |
+
self.top_k = top_k
|
346 |
+
self.max_cache_size = max_cache_size
|
347 |
+
|
348 |
+
def forward(
|
349 |
+
self,
|
350 |
+
hidden_states: torch.Tensor,
|
351 |
+
attention_mask: Optional[torch.Tensor] = None,
|
352 |
+
position_ids: Optional[torch.LongTensor] = None,
|
353 |
+
past_key_value: Optional[Tuple[torch.Tensor]] = None,
|
354 |
+
output_attentions: bool = False,
|
355 |
+
use_cache: bool = False,
|
356 |
+
is_mem: Optional[torch.Tensor] = None,
|
357 |
+
last_section_mask: Optional[torch.Tensor] = None,
|
358 |
+
offload_cache_to_cpu: bool = False,
|
359 |
+
) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
|
360 |
+
bsz, q_len, _ = hidden_states.size()
|
361 |
+
|
362 |
+
query_states = (
|
363 |
+
self.q_proj(hidden_states)
|
364 |
+
.view(bsz, q_len, self.num_heads, self.head_dim)
|
365 |
+
.transpose(1, 2)
|
366 |
+
)
|
367 |
+
key_states = (
|
368 |
+
self.k_proj(hidden_states)
|
369 |
+
.view(bsz, q_len, self.num_heads, self.head_dim)
|
370 |
+
.transpose(1, 2)
|
371 |
+
)
|
372 |
+
value_states = (
|
373 |
+
self.v_proj(hidden_states)
|
374 |
+
.view(bsz, q_len, self.num_heads, self.head_dim)
|
375 |
+
.transpose(1, 2)
|
376 |
+
)
|
377 |
+
|
378 |
+
kv_seq_len = key_states.shape[-2]
|
379 |
+
if past_key_value is not None:
|
380 |
+
kv_seq_len += past_key_value[0].shape[-2]
|
381 |
+
if len(past_key_value) > 2:
|
382 |
+
kv_seq_len += past_key_value[3].shape[2] * past_key_value[3].shape[3]
|
383 |
+
cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
|
384 |
+
key_states_before_pos = key_states
|
385 |
+
query_states, key_states = apply_rotary_pos_emb(
|
386 |
+
query_states, key_states, cos, sin, position_ids
|
387 |
+
)
|
388 |
+
# [bsz, nh, t, hd]
|
389 |
+
|
390 |
+
attn_prefix = None
|
391 |
+
if past_key_value is not None:
|
392 |
+
# reuse k, v, self_attention
|
393 |
+
if self.mem_freq is None:
|
394 |
+
cache_len = past_key_value[0].shape[2]
|
395 |
+
if self.max_cache_size is not None:
|
396 |
+
cache_len = min(cache_len, self.max_cache_size)
|
397 |
+
if is_mem is not None:
|
398 |
+
is_mem = torch.cat(
|
399 |
+
(is_mem.new_zeros((1, 1, q_len, cache_len)), is_mem), dim=-1
|
400 |
+
)
|
401 |
+
last_section_mask = torch.cat(
|
402 |
+
(
|
403 |
+
last_section_mask.new_ones((1, 1, q_len, cache_len)),
|
404 |
+
last_section_mask,
|
405 |
+
),
|
406 |
+
dim=-1,
|
407 |
+
)
|
408 |
+
|
409 |
+
past_key_states = torch.cat([past_key_value[0], key_states], dim=2)
|
410 |
+
past_value_states = torch.cat([past_key_value[1], value_states], dim=2)
|
411 |
+
key_states = past_key_states[:, :, -(q_len + cache_len) :]
|
412 |
+
value_states = past_value_states[:, :, -(q_len + cache_len) :]
|
413 |
+
expected_att_size = (bsz, self.num_heads, q_len, cache_len + q_len)
|
414 |
+
else:
|
415 |
+
orig_value_states = value_states
|
416 |
+
|
417 |
+
incomplete_len = past_key_value[0].shape[2] % (self.mem_freq + 1)
|
418 |
+
full_len = past_key_value[0].shape[2] - incomplete_len
|
419 |
+
past_key_mem, past_key_incomplete = torch.split(
|
420 |
+
past_key_value[0], (full_len, incomplete_len), dim=2
|
421 |
+
)
|
422 |
+
past_value_mem, past_value_incomplete = torch.split(
|
423 |
+
past_key_value[1], (full_len, incomplete_len), dim=2
|
424 |
+
)
|
425 |
+
|
426 |
+
if offload_cache_to_cpu:
|
427 |
+
past_key_value = (
|
428 |
+
past_key_incomplete,
|
429 |
+
past_value_incomplete,
|
430 |
+
*past_key_value[2:],
|
431 |
+
)
|
432 |
+
|
433 |
+
if incomplete_len > 0:
|
434 |
+
assert q_len + incomplete_len <= (self.mem_freq + 1)
|
435 |
+
is_mem = torch.cat(
|
436 |
+
(is_mem.new_zeros((1, 1, q_len, incomplete_len)), is_mem), dim=-1
|
437 |
+
)
|
438 |
+
last_section_mask = torch.cat(
|
439 |
+
(
|
440 |
+
last_section_mask.new_ones((1, 1, q_len, incomplete_len)),
|
441 |
+
last_section_mask,
|
442 |
+
),
|
443 |
+
dim=-1,
|
444 |
+
)
|
445 |
+
|
446 |
+
if len(past_key_value) > 2:
|
447 |
+
full_len += past_key_value[3].shape[2] * past_key_value[3].shape[3]
|
448 |
+
past_key_incomplete_pos = torch.arange(
|
449 |
+
full_len,
|
450 |
+
full_len + incomplete_len,
|
451 |
+
dtype=torch.long,
|
452 |
+
device=position_ids.device,
|
453 |
+
).unsqueeze(0)
|
454 |
+
_, past_key_incomplete = apply_rotary_pos_emb(
|
455 |
+
None, past_key_incomplete, cos, sin, past_key_incomplete_pos
|
456 |
+
)
|
457 |
+
key_states = torch.cat((past_key_incomplete, key_states), dim=2)
|
458 |
+
value_states = torch.cat((past_value_incomplete, value_states), dim=2)
|
459 |
+
|
460 |
+
past_key_mem = past_key_mem.view(
|
461 |
+
bsz, self.num_heads, -1, self.mem_freq + 1, self.head_dim
|
462 |
+
)
|
463 |
+
past_value_mem = past_value_mem.view(
|
464 |
+
bsz, self.num_heads, -1, self.mem_freq + 1, self.head_dim
|
465 |
+
)
|
466 |
+
|
467 |
+
if len(past_key_value) > 2:
|
468 |
+
mem_key_nopos = torch.cat(
|
469 |
+
(
|
470 |
+
past_key_value[2],
|
471 |
+
past_key_mem.select(dim=3, index=self.mem_freq),
|
472 |
+
),
|
473 |
+
dim=2,
|
474 |
+
)
|
475 |
+
past_key_mem_offload = past_key_value[3]
|
476 |
+
past_key_mem = torch.cat(
|
477 |
+
(
|
478 |
+
past_key_mem_offload,
|
479 |
+
past_key_mem.to(past_key_mem_offload.device),
|
480 |
+
),
|
481 |
+
dim=2,
|
482 |
+
)
|
483 |
+
past_value_mem = torch.cat(
|
484 |
+
(
|
485 |
+
past_key_value[4],
|
486 |
+
past_value_mem.to(past_key_mem_offload.device),
|
487 |
+
),
|
488 |
+
dim=2,
|
489 |
+
)
|
490 |
+
else:
|
491 |
+
mem_key_nopos = past_key_mem.select(dim=3, index=self.mem_freq)
|
492 |
+
|
493 |
+
num_mems = past_key_mem.shape[2]
|
494 |
+
top_k = min(self.top_k, num_mems)
|
495 |
+
prefix_len = full_len - (top_k + 1) * (self.mem_freq + 1)
|
496 |
+
mem_indices = torch.cat(
|
497 |
+
(
|
498 |
+
position_ids.new_zeros((max(0, num_mems - top_k),)),
|
499 |
+
torch.arange(
|
500 |
+
1,
|
501 |
+
top_k + 1,
|
502 |
+
device=query_states.device,
|
503 |
+
dtype=position_ids.dtype,
|
504 |
+
),
|
505 |
+
),
|
506 |
+
dim=0,
|
507 |
+
)
|
508 |
+
mem_pos = (mem_indices * (self.mem_freq + 1) + self.mem_freq).unsqueeze(
|
509 |
+
0
|
510 |
+
).expand(bsz, -1) + prefix_len
|
511 |
+
_, mem_key = apply_rotary_pos_emb(
|
512 |
+
None, mem_key_nopos, cos, sin, mem_pos
|
513 |
+
)
|
514 |
+
mem_attn_weights = torch.matmul(
|
515 |
+
query_states, mem_key.transpose(2, 3)
|
516 |
+
) / math.sqrt(self.head_dim)
|
517 |
+
|
518 |
+
if offload_cache_to_cpu:
|
519 |
+
aggregate = "max_over_tokens"
|
520 |
+
else:
|
521 |
+
aggregate = None
|
522 |
+
if aggregate == "max_over_tokens":
|
523 |
+
token_retrievers = 1
|
524 |
+
head_retrievers = self.num_heads
|
525 |
+
mem_attn_weights = torch.nn.functional.softmax(
|
526 |
+
mem_attn_weights, dim=-1
|
527 |
+
)
|
528 |
+
mem_attn_weights = mem_attn_weights.amax(dim=2, keepdim=True)
|
529 |
+
elif aggregate is None:
|
530 |
+
token_retrievers = q_len
|
531 |
+
head_retrievers = self.num_heads
|
532 |
+
else:
|
533 |
+
raise NotImplementedError()
|
534 |
+
|
535 |
+
mem_selected_idx = (
|
536 |
+
mem_attn_weights.topk(dim=-1, k=top_k)[1]
|
537 |
+
.sort(dim=-1)[0]
|
538 |
+
.view(bsz, head_retrievers, token_retrievers, top_k)
|
539 |
+
)
|
540 |
+
|
541 |
+
selected_indices = torch.arange(
|
542 |
+
0,
|
543 |
+
top_k * (self.mem_freq + 1),
|
544 |
+
device=query_states.device,
|
545 |
+
dtype=position_ids.dtype,
|
546 |
+
)
|
547 |
+
selected_indices = torch.where(
|
548 |
+
mem_selected_idx >= num_mems - top_k, self.mem_freq + 1, 0
|
549 |
+
).unsqueeze(-1) + selected_indices.view(
|
550 |
+
1, 1, 1, top_k, self.mem_freq + 1
|
551 |
+
)
|
552 |
+
selected_indices = (
|
553 |
+
selected_indices.view(
|
554 |
+
bsz, head_retrievers, token_retrievers, -1
|
555 |
+
).expand(bsz, self.num_heads, q_len, -1)
|
556 |
+
+ prefix_len
|
557 |
+
)
|
558 |
+
|
559 |
+
mem_selected_idx = mem_selected_idx.to(past_key_mem.device)
|
560 |
+
|
561 |
+
mem_selected_idx = mem_selected_idx.view(
|
562 |
+
bsz, self.num_heads, token_retrievers, top_k, 1, 1
|
563 |
+
).expand(
|
564 |
+
bsz,
|
565 |
+
self.num_heads,
|
566 |
+
token_retrievers,
|
567 |
+
top_k,
|
568 |
+
self.mem_freq + 1,
|
569 |
+
self.head_dim,
|
570 |
+
)
|
571 |
+
selected_keys = past_key_mem.unsqueeze(2).expand(
|
572 |
+
bsz,
|
573 |
+
self.num_heads,
|
574 |
+
token_retrievers,
|
575 |
+
-1,
|
576 |
+
self.mem_freq + 1,
|
577 |
+
self.head_dim,
|
578 |
+
)
|
579 |
+
selected_keys = selected_keys.take_along_dim(
|
580 |
+
mem_selected_idx, dim=3
|
581 |
+
).to(query_states.device)
|
582 |
+
selected_values = (
|
583 |
+
past_value_mem.unsqueeze(2)
|
584 |
+
.expand(
|
585 |
+
bsz,
|
586 |
+
self.num_heads,
|
587 |
+
token_retrievers,
|
588 |
+
-1,
|
589 |
+
self.mem_freq + 1,
|
590 |
+
self.head_dim,
|
591 |
+
)
|
592 |
+
.take_along_dim(mem_selected_idx, dim=3)
|
593 |
+
.to(query_states.device)
|
594 |
+
)
|
595 |
+
|
596 |
+
selected_keys = selected_keys.view(
|
597 |
+
bsz, self.num_heads, token_retrievers, -1, self.head_dim
|
598 |
+
).expand(bsz, self.num_heads, q_len, -1, self.head_dim)
|
599 |
+
selected_keys = apply_rotary_pos_emb(
|
600 |
+
None, selected_keys.unsqueeze(1), cos, sin, selected_indices
|
601 |
+
)[1].squeeze(1)
|
602 |
+
selected_values = selected_values.view(
|
603 |
+
bsz, self.num_heads, token_retrievers, -1, self.head_dim
|
604 |
+
).expand(bsz, self.num_heads, q_len, -1, self.head_dim)
|
605 |
+
attn_prefix = torch.matmul(
|
606 |
+
query_states.unsqueeze(3), selected_keys.transpose(3, 4)
|
607 |
+
).squeeze(3) / math.sqrt(self.head_dim)
|
608 |
+
is_mem_prefix = (
|
609 |
+
torch.cat(
|
610 |
+
(is_mem.new_zeros((self.mem_freq,)), is_mem.new_ones((1,)))
|
611 |
+
)
|
612 |
+
.unsqueeze(0)
|
613 |
+
.repeat((top_k, 1))
|
614 |
+
)
|
615 |
+
is_mem_prefix = is_mem_prefix.view(1, 1, 1, -1).expand(1, 1, q_len, -1)
|
616 |
+
is_mem = torch.cat((is_mem_prefix, is_mem), dim=-1)
|
617 |
+
last_section_mask = torch.cat(
|
618 |
+
(
|
619 |
+
last_section_mask.new_zeros(
|
620 |
+
(1, 1, q_len, top_k * (self.mem_freq + 1))
|
621 |
+
),
|
622 |
+
last_section_mask,
|
623 |
+
),
|
624 |
+
dim=-1,
|
625 |
+
)
|
626 |
+
expected_att_size = (bsz, self.num_heads, q_len, q_len + incomplete_len)
|
627 |
+
|
628 |
+
past_key_states = torch.cat(
|
629 |
+
[past_key_value[0], key_states_before_pos], dim=2
|
630 |
+
)
|
631 |
+
past_value_states = torch.cat(
|
632 |
+
[past_key_value[1], orig_value_states], dim=2
|
633 |
+
)
|
634 |
+
|
635 |
+
if offload_cache_to_cpu:
|
636 |
+
past_key_value = (
|
637 |
+
(
|
638 |
+
past_key_states,
|
639 |
+
past_value_states,
|
640 |
+
mem_key_nopos,
|
641 |
+
past_key_mem.to("cpu"),
|
642 |
+
past_value_mem.to("cpu"),
|
643 |
+
*past_key_value[5:],
|
644 |
+
)
|
645 |
+
if use_cache
|
646 |
+
else None
|
647 |
+
)
|
648 |
+
else:
|
649 |
+
past_key_value = (
|
650 |
+
(past_key_states, past_value_states) if use_cache else None
|
651 |
+
)
|
652 |
+
|
653 |
+
else:
|
654 |
+
if self.mem_freq is None:
|
655 |
+
past_key_states = key_states
|
656 |
+
else:
|
657 |
+
past_key_states = key_states_before_pos
|
658 |
+
past_value_states = value_states
|
659 |
+
expected_att_size = (bsz, self.num_heads, q_len, kv_seq_len)
|
660 |
+
past_key_value = (past_key_states, past_value_states) if use_cache else None
|
661 |
+
|
662 |
+
attn_weights = torch.matmul(
|
663 |
+
query_states, key_states.transpose(2, 3)
|
664 |
+
) / math.sqrt(self.head_dim)
|
665 |
+
if attn_weights.size() != expected_att_size:
|
666 |
+
raise ValueError(
|
667 |
+
f"Attention weights should be of size {(bsz, self.num_heads, q_len, kv_seq_len)}, but is"
|
668 |
+
f" {attn_weights.size()}"
|
669 |
+
)
|
670 |
+
|
671 |
+
if attention_mask is not None:
|
672 |
+
if attention_mask.size() != (bsz, 1, q_len, kv_seq_len):
|
673 |
+
raise ValueError(
|
674 |
+
f"Attention mask should be of size {(bsz, 1, q_len, kv_seq_len)}, but is {attention_mask.size()}"
|
675 |
+
)
|
676 |
+
attn_weights = attn_weights + attention_mask[..., -attn_weights.shape[-1] :]
|
677 |
+
attn_weights = torch.max(
|
678 |
+
attn_weights, torch.tensor(torch.finfo(attn_weights.dtype).min)
|
679 |
+
)
|
680 |
+
if attn_prefix is not None:
|
681 |
+
attn_weights = torch.cat((attn_prefix, attn_weights), dim=-1)
|
682 |
+
# upcast attention to fp32
|
683 |
+
if is_mem is None:
|
684 |
+
raise ValueError("Don't use this without landmarks")
|
685 |
+
# attn_weights = nn.functional.softmax(
|
686 |
+
# attn_weights, dim=-1, dtype=torch.float32
|
687 |
+
# ).to(query_states.dtype)
|
688 |
+
else:
|
689 |
+
attn_weights = landmark_grouped_softmax(
|
690 |
+
attn_weights,
|
691 |
+
dim=-1,
|
692 |
+
is_mem=is_mem.expand(-1, self.num_heads, -1, -1),
|
693 |
+
last_section_mask=last_section_mask,
|
694 |
+
).to(query_states.dtype)
|
695 |
+
if attn_prefix is not None:
|
696 |
+
attn_prefix, attn_weights = torch.split(
|
697 |
+
attn_weights,
|
698 |
+
(attn_prefix.shape[-1], attn_weights.shape[-1] - attn_prefix.shape[-1]),
|
699 |
+
dim=-1,
|
700 |
+
)
|
701 |
+
attn_output = torch.matmul(attn_weights, value_states)
|
702 |
+
if attn_prefix is not None:
|
703 |
+
attn_output += torch.matmul(
|
704 |
+
attn_prefix.unsqueeze(3), selected_values
|
705 |
+
).squeeze(3)
|
706 |
+
|
707 |
+
if attn_output.size() != (bsz, self.num_heads, q_len, self.head_dim):
|
708 |
+
raise ValueError(
|
709 |
+
f"`attn_output` should be of size {(bsz, self.num_heads, q_len, self.head_dim)}, but is"
|
710 |
+
f" {attn_output.size()}"
|
711 |
+
)
|
712 |
+
|
713 |
+
attn_output = attn_output.transpose(1, 2)
|
714 |
+
attn_output = attn_output.reshape(bsz, q_len, self.hidden_size)
|
715 |
+
|
716 |
+
attn_output = self.o_proj(attn_output)
|
717 |
+
|
718 |
+
if not output_attentions:
|
719 |
+
attn_weights = None
|
720 |
+
|
721 |
+
return attn_output, attn_weights, past_key_value
|
722 |
+
|
723 |
+
|
724 |
+
class LlamaDecoderLayer(nn.Module):
|
725 |
+
def __init__(self, config: LlamaConfig):
|
726 |
+
super().__init__()
|
727 |
+
self.hidden_size = config.hidden_size
|
728 |
+
self.self_attn = LlamaAttention(config=config)
|
729 |
+
self.mlp = LlamaMLP(
|
730 |
+
hidden_size=self.hidden_size,
|
731 |
+
intermediate_size=config.intermediate_size,
|
732 |
+
hidden_act=config.hidden_act,
|
733 |
+
)
|
734 |
+
self.input_layernorm = LlamaRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
|
735 |
+
self.post_attention_layernorm = LlamaRMSNorm(
|
736 |
+
config.hidden_size, eps=config.rms_norm_eps
|
737 |
+
)
|
738 |
+
|
739 |
+
def set_mem_cache_args(self, mem_freq, top_k, max_cache_size):
|
740 |
+
self.self_attn.set_mem_cache_args(mem_freq, top_k, max_cache_size)
|
741 |
+
|
742 |
+
def forward(
|
743 |
+
self,
|
744 |
+
hidden_states: torch.Tensor,
|
745 |
+
attention_mask: Optional[torch.Tensor] = None,
|
746 |
+
position_ids: Optional[torch.LongTensor] = None,
|
747 |
+
past_key_value: Optional[Tuple[torch.Tensor]] = None,
|
748 |
+
output_attentions: Optional[bool] = False,
|
749 |
+
use_cache: Optional[bool] = False,
|
750 |
+
is_mem: Optional[torch.Tensor] = None,
|
751 |
+
last_section_mask: Optional[torch.Tensor] = None,
|
752 |
+
offload_cache_to_cpu: bool = False,
|
753 |
+
) -> Tuple[
|
754 |
+
torch.FloatTensor, Optional[Tuple[torch.FloatTensor, torch.FloatTensor]]
|
755 |
+
]:
|
756 |
+
"""
|
757 |
+
Args:
|
758 |
+
hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
|
759 |
+
attention_mask (`torch.FloatTensor`, *optional*): attention mask of size
|
760 |
+
`(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
|
761 |
+
output_attentions (`bool`, *optional*):
|
762 |
+
Whether or not to return the attentions tensors of all attention layers. See `attentions` under
|
763 |
+
returned tensors for more detail.
|
764 |
+
use_cache (`bool`, *optional*):
|
765 |
+
If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
|
766 |
+
(see `past_key_values`).
|
767 |
+
past_key_value (`Tuple(torch.FloatTensor)`, *optional*): cached past key and value projection states
|
768 |
+
"""
|
769 |
+
|
770 |
+
residual = hidden_states
|
771 |
+
|
772 |
+
hidden_states = self.input_layernorm(hidden_states)
|
773 |
+
|
774 |
+
# Self Attention
|
775 |
+
hidden_states, self_attn_weights, present_key_value = self.self_attn(
|
776 |
+
hidden_states=hidden_states,
|
777 |
+
attention_mask=attention_mask,
|
778 |
+
position_ids=position_ids,
|
779 |
+
past_key_value=past_key_value,
|
780 |
+
output_attentions=output_attentions,
|
781 |
+
use_cache=use_cache,
|
782 |
+
is_mem=is_mem,
|
783 |
+
last_section_mask=last_section_mask,
|
784 |
+
offload_cache_to_cpu=offload_cache_to_cpu,
|
785 |
+
)
|
786 |
+
hidden_states = residual + hidden_states
|
787 |
+
|
788 |
+
# Fully Connected
|
789 |
+
residual = hidden_states
|
790 |
+
hidden_states = self.post_attention_layernorm(hidden_states)
|
791 |
+
hidden_states = self.mlp(hidden_states)
|
792 |
+
hidden_states = residual + hidden_states
|
793 |
+
|
794 |
+
outputs = (hidden_states,)
|
795 |
+
|
796 |
+
if output_attentions:
|
797 |
+
outputs += (self_attn_weights,)
|
798 |
+
|
799 |
+
if use_cache:
|
800 |
+
outputs += (present_key_value,)
|
801 |
+
|
802 |
+
return outputs
|
803 |
+
|
804 |
+
|
805 |
+
LLAMA_START_DOCSTRING = r"""
|
806 |
+
This model inherits from [`PreTrainedModel`]. Check the superclass documentation for the generic methods the
|
807 |
+
library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads
|
808 |
+
etc.)
|
809 |
+
|
810 |
+
This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass.
|
811 |
+
Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage
|
812 |
+
and behavior.
|
813 |
+
|
814 |
+
Parameters:
|
815 |
+
config ([`LlamaConfig`]):
|
816 |
+
Model configuration class with all the parameters of the model. Initializing with a config file does not
|
817 |
+
load the weights associated with the model, only the configuration. Check out the
|
818 |
+
[`~PreTrainedModel.from_pretrained`] method to load the model weights.
|
819 |
+
"""
|
820 |
+
|
821 |
+
|
822 |
+
@add_start_docstrings(
|
823 |
+
"The bare LLaMA Model outputting raw hidden-states without any specific head on top.",
|
824 |
+
LLAMA_START_DOCSTRING,
|
825 |
+
)
|
826 |
+
class LlamaPreTrainedModel(PreTrainedModel):
|
827 |
+
config_class = LlamaConfig
|
828 |
+
base_model_prefix = "model"
|
829 |
+
supports_gradient_checkpointing = True
|
830 |
+
_no_split_modules = ["LlamaDecoderLayer"]
|
831 |
+
_keys_to_ignore_on_load_unexpected = [r"decoder\.version"]
|
832 |
+
|
833 |
+
def _init_weights(self, module):
|
834 |
+
std = self.config.initializer_range
|
835 |
+
if isinstance(module, nn.Linear):
|
836 |
+
module.weight.data.normal_(mean=0.0, std=std)
|
837 |
+
if module.bias is not None:
|
838 |
+
module.bias.data.zero_()
|
839 |
+
elif isinstance(module, nn.Embedding):
|
840 |
+
module.weight.data.normal_(mean=0.0, std=std)
|
841 |
+
if module.padding_idx is not None:
|
842 |
+
module.weight.data[module.padding_idx].zero_()
|
843 |
+
|
844 |
+
def _set_gradient_checkpointing(self, module, value=False):
|
845 |
+
if isinstance(module, LlamaModel):
|
846 |
+
module.gradient_checkpointing = value
|
847 |
+
|
848 |
+
|
849 |
+
LLAMA_INPUTS_DOCSTRING = r"""
|
850 |
+
Args:
|
851 |
+
input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`):
|
852 |
+
Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide
|
853 |
+
it.
|
854 |
+
|
855 |
+
Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
|
856 |
+
[`PreTrainedTokenizer.__call__`] for details.
|
857 |
+
|
858 |
+
[What are input IDs?](../glossary#input-ids)
|
859 |
+
attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
|
860 |
+
Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:
|
861 |
+
|
862 |
+
- 1 for tokens that are **not masked**,
|
863 |
+
- 0 for tokens that are **masked**.
|
864 |
+
|
865 |
+
[What are attention masks?](../glossary#attention-mask)
|
866 |
+
|
867 |
+
Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
|
868 |
+
[`PreTrainedTokenizer.__call__`] for details.
|
869 |
+
|
870 |
+
If `past_key_values` is used, optionally only the last `decoder_input_ids` have to be input (see
|
871 |
+
`past_key_values`).
|
872 |
+
|
873 |
+
If you want to change padding behavior, you should read [`modeling_opt._prepare_decoder_attention_mask`]
|
874 |
+
and modify to your needs. See diagram 1 in [the paper](https://arxiv.org/abs/1910.13461) for more
|
875 |
+
information on the default strategy.
|
876 |
+
|
877 |
+
- 1 indicates the head is **not masked**,
|
878 |
+
- 0 indicates the head is **masked**.
|
879 |
+
position_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
|
880 |
+
Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0,
|
881 |
+
config.n_positions - 1]`.
|
882 |
+
|
883 |
+
[What are position IDs?](../glossary#position-ids)
|
884 |
+
past_key_values (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
|
885 |
+
Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape
|
886 |
+
`(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape
|
887 |
+
`(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.
|
888 |
+
|
889 |
+
Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
|
890 |
+
blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.
|
891 |
+
|
892 |
+
If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that
|
893 |
+
don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of all
|
894 |
+
`decoder_input_ids` of shape `(batch_size, sequence_length)`.
|
895 |
+
inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
|
896 |
+
Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
|
897 |
+
is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
|
898 |
+
model's internal embedding lookup matrix.
|
899 |
+
use_cache (`bool`, *optional*):
|
900 |
+
If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
|
901 |
+
`past_key_values`).
|
902 |
+
output_attentions (`bool`, *optional*):
|
903 |
+
Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
|
904 |
+
tensors for more detail.
|
905 |
+
output_hidden_states (`bool`, *optional*):
|
906 |
+
Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
|
907 |
+
more detail.
|
908 |
+
return_dict (`bool`, *optional*):
|
909 |
+
Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
|
910 |
+
"""
|
911 |
+
|
912 |
+
|
913 |
+
@add_start_docstrings(
|
914 |
+
"The bare LLaMA Model outputting raw hidden-states without any specific head on top.",
|
915 |
+
LLAMA_START_DOCSTRING,
|
916 |
+
)
|
917 |
+
class LlamaModel(LlamaPreTrainedModel):
|
918 |
+
"""
|
919 |
+
Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`LlamaDecoderLayer`]
|
920 |
+
|
921 |
+
Args:
|
922 |
+
config: LlamaConfig
|
923 |
+
"""
|
924 |
+
|
925 |
+
def __init__(self, config: LlamaConfig):
|
926 |
+
super().__init__(config)
|
927 |
+
self.padding_idx = config.pad_token_id
|
928 |
+
self.vocab_size = config.vocab_size
|
929 |
+
|
930 |
+
self.embed_tokens = nn.Embedding(
|
931 |
+
config.vocab_size, config.hidden_size, self.padding_idx
|
932 |
+
)
|
933 |
+
self.layers = nn.ModuleList(
|
934 |
+
[LlamaDecoderLayer(config) for _ in range(config.num_hidden_layers)]
|
935 |
+
)
|
936 |
+
self.norm = LlamaRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
|
937 |
+
|
938 |
+
self.mem_id = None
|
939 |
+
|
940 |
+
self.gradient_checkpointing = False
|
941 |
+
# Initialize weights and apply final processing
|
942 |
+
self.post_init()
|
943 |
+
|
944 |
+
def get_input_embeddings(self):
|
945 |
+
return self.embed_tokens
|
946 |
+
|
947 |
+
def set_input_embeddings(self, value):
|
948 |
+
self.embed_tokens = value
|
949 |
+
|
950 |
+
def set_mem_id(self, mem_id):
|
951 |
+
self.mem_id = mem_id
|
952 |
+
|
953 |
+
def set_mem_cache_args(self, mem_freq, top_k, max_cache_size):
|
954 |
+
for layer in self.layers:
|
955 |
+
layer.set_mem_cache_args(mem_freq, top_k, max_cache_size)
|
956 |
+
|
957 |
+
# Copied from transformers.models.bart.modeling_bart.BartDecoder._prepare_decoder_attention_mask
|
958 |
+
def _prepare_decoder_attention_mask(
|
959 |
+
self, attention_mask, input_shape, inputs_embeds, past_key_values_length
|
960 |
+
):
|
961 |
+
# create causal mask
|
962 |
+
# [bsz, seq_len] -> [bsz, 1, tgt_seq_len, src_seq_len]
|
963 |
+
combined_attention_mask = None
|
964 |
+
if input_shape[-1] > 1:
|
965 |
+
combined_attention_mask = _make_causal_mask(
|
966 |
+
input_shape,
|
967 |
+
inputs_embeds.dtype,
|
968 |
+
device=inputs_embeds.device,
|
969 |
+
past_key_values_length=past_key_values_length,
|
970 |
+
)
|
971 |
+
|
972 |
+
if attention_mask is not None:
|
973 |
+
# [bsz, seq_len] -> [bsz, 1, tgt_seq_len, src_seq_len]
|
974 |
+
expanded_attn_mask = _expand_mask(
|
975 |
+
attention_mask, inputs_embeds.dtype, tgt_len=input_shape[-1]
|
976 |
+
).to(inputs_embeds.device)
|
977 |
+
combined_attention_mask = (
|
978 |
+
expanded_attn_mask
|
979 |
+
if combined_attention_mask is None
|
980 |
+
else expanded_attn_mask + combined_attention_mask
|
981 |
+
)
|
982 |
+
|
983 |
+
return combined_attention_mask
|
984 |
+
|
985 |
+
@add_start_docstrings_to_model_forward(LLAMA_INPUTS_DOCSTRING)
|
986 |
+
def forward(
|
987 |
+
self,
|
988 |
+
input_ids: torch.LongTensor = None,
|
989 |
+
attention_mask: Optional[torch.Tensor] = None,
|
990 |
+
position_ids: Optional[torch.LongTensor] = None,
|
991 |
+
past_key_values: Optional[List[torch.FloatTensor]] = None,
|
992 |
+
inputs_embeds: Optional[torch.FloatTensor] = None,
|
993 |
+
use_cache: Optional[bool] = None,
|
994 |
+
output_attentions: Optional[bool] = None,
|
995 |
+
output_hidden_states: Optional[bool] = None,
|
996 |
+
return_dict: Optional[bool] = None,
|
997 |
+
offload_cache_to_cpu: Optional[bool] = None,
|
998 |
+
) -> Union[Tuple, BaseModelOutputWithPast]:
|
999 |
+
output_attentions = (
|
1000 |
+
output_attentions
|
1001 |
+
if output_attentions is not None
|
1002 |
+
else self.config.output_attentions
|
1003 |
+
)
|
1004 |
+
output_hidden_states = (
|
1005 |
+
output_hidden_states
|
1006 |
+
if output_hidden_states is not None
|
1007 |
+
else self.config.output_hidden_states
|
1008 |
+
)
|
1009 |
+
use_cache = use_cache if use_cache is not None else self.config.use_cache
|
1010 |
+
|
1011 |
+
return_dict = (
|
1012 |
+
return_dict if return_dict is not None else self.config.use_return_dict
|
1013 |
+
)
|
1014 |
+
|
1015 |
+
# retrieve input_ids and inputs_embeds
|
1016 |
+
is_mem = None
|
1017 |
+
if input_ids is not None and inputs_embeds is not None:
|
1018 |
+
raise ValueError(
|
1019 |
+
"You cannot specify both decoder_input_ids and decoder_inputs_embeds at the same time"
|
1020 |
+
)
|
1021 |
+
elif input_ids is not None:
|
1022 |
+
batch_size, seq_length = input_ids.shape
|
1023 |
+
if self.mem_id is not None:
|
1024 |
+
with torch.no_grad():
|
1025 |
+
is_mem = input_ids == self.mem_id
|
1026 |
+
elif inputs_embeds is not None:
|
1027 |
+
batch_size, seq_length, _ = inputs_embeds.shape
|
1028 |
+
if self.mem_id is not None:
|
1029 |
+
raise NotImplementedError
|
1030 |
+
else:
|
1031 |
+
raise ValueError(
|
1032 |
+
"You have to specify either decoder_input_ids or decoder_inputs_embeds"
|
1033 |
+
)
|
1034 |
+
|
1035 |
+
seq_length_with_past = seq_length
|
1036 |
+
past_key_values_length = 0
|
1037 |
+
|
1038 |
+
if past_key_values is not None:
|
1039 |
+
if is_mem is not None:
|
1040 |
+
pass
|
1041 |
+
# raise NotImplementedError
|
1042 |
+
past_key_values_length = past_key_values[0][0].shape[2]
|
1043 |
+
if len(past_key_values[0]) > 2:
|
1044 |
+
past_key_values_length += (
|
1045 |
+
past_key_values[0][3].shape[2] * past_key_values[0][3].shape[3]
|
1046 |
+
)
|
1047 |
+
seq_length_with_past = seq_length_with_past + past_key_values_length
|
1048 |
+
|
1049 |
+
if position_ids is None:
|
1050 |
+
device = input_ids.device if input_ids is not None else inputs_embeds.device
|
1051 |
+
position_ids = torch.arange(
|
1052 |
+
past_key_values_length,
|
1053 |
+
seq_length + past_key_values_length,
|
1054 |
+
dtype=torch.long,
|
1055 |
+
device=device,
|
1056 |
+
)
|
1057 |
+
position_ids = position_ids.unsqueeze(0).view(-1, seq_length)
|
1058 |
+
else:
|
1059 |
+
position_ids = position_ids.view(-1, seq_length).long()
|
1060 |
+
|
1061 |
+
if inputs_embeds is None:
|
1062 |
+
inputs_embeds = self.embed_tokens(input_ids)
|
1063 |
+
# embed positions
|
1064 |
+
if attention_mask is None:
|
1065 |
+
attention_mask = torch.ones(
|
1066 |
+
(batch_size, seq_length_with_past),
|
1067 |
+
dtype=torch.bool,
|
1068 |
+
device=inputs_embeds.device,
|
1069 |
+
)
|
1070 |
+
attention_mask = self._prepare_decoder_attention_mask(
|
1071 |
+
attention_mask,
|
1072 |
+
(batch_size, seq_length),
|
1073 |
+
inputs_embeds,
|
1074 |
+
past_key_values_length,
|
1075 |
+
)
|
1076 |
+
|
1077 |
+
last_section_mask = None
|
1078 |
+
if is_mem is not None:
|
1079 |
+
is_mem = is_mem.unsqueeze(1).unsqueeze(2)
|
1080 |
+
current_len = input_ids.shape[1]
|
1081 |
+
mem_ids = torch.where(
|
1082 |
+
attention_mask[..., -current_len:] < -1,
|
1083 |
+
0,
|
1084 |
+
torch.cumsum(is_mem, -1) - is_mem.int(),
|
1085 |
+
)
|
1086 |
+
last_section_mask = torch.amax(mem_ids, -1, keepdim=True) == mem_ids
|
1087 |
+
attention_mask[..., -current_len:].masked_fill_(
|
1088 |
+
last_section_mask & is_mem,
|
1089 |
+
torch.tensor(
|
1090 |
+
torch.finfo(inputs_embeds.dtype).min, device=inputs_embeds.device
|
1091 |
+
),
|
1092 |
+
)
|
1093 |
+
last_section_mask.logical_and_(attention_mask[..., -current_len:] > -1)
|
1094 |
+
is_mem = is_mem.logical_and(attention_mask[..., -current_len:] > -1)
|
1095 |
+
|
1096 |
+
hidden_states = inputs_embeds
|
1097 |
+
|
1098 |
+
if self.gradient_checkpointing and self.training:
|
1099 |
+
if use_cache:
|
1100 |
+
logger.warning_once(
|
1101 |
+
"`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
|
1102 |
+
)
|
1103 |
+
use_cache = False
|
1104 |
+
|
1105 |
+
# decoder layers
|
1106 |
+
all_hidden_states = () if output_hidden_states else None
|
1107 |
+
all_self_attns = () if output_attentions else None
|
1108 |
+
next_decoder_cache = () if use_cache else None
|
1109 |
+
|
1110 |
+
for idx, decoder_layer in enumerate(self.layers):
|
1111 |
+
if output_hidden_states:
|
1112 |
+
all_hidden_states += (hidden_states,)
|
1113 |
+
|
1114 |
+
past_key_value = (
|
1115 |
+
past_key_values[idx] if past_key_values is not None else None
|
1116 |
+
)
|
1117 |
+
|
1118 |
+
if self.gradient_checkpointing and self.training:
|
1119 |
+
|
1120 |
+
def create_custom_forward(module):
|
1121 |
+
def custom_forward(*inputs):
|
1122 |
+
# None for past_key_value
|
1123 |
+
return module(*inputs)
|
1124 |
+
|
1125 |
+
return custom_forward
|
1126 |
+
|
1127 |
+
layer_outputs = torch.utils.checkpoint.checkpoint(
|
1128 |
+
create_custom_forward(decoder_layer),
|
1129 |
+
hidden_states,
|
1130 |
+
attention_mask,
|
1131 |
+
position_ids,
|
1132 |
+
None,
|
1133 |
+
output_attentions,
|
1134 |
+
None,
|
1135 |
+
is_mem,
|
1136 |
+
last_section_mask,
|
1137 |
+
)
|
1138 |
+
else:
|
1139 |
+
layer_outputs = decoder_layer(
|
1140 |
+
hidden_states,
|
1141 |
+
attention_mask=attention_mask,
|
1142 |
+
position_ids=position_ids,
|
1143 |
+
past_key_value=past_key_value,
|
1144 |
+
output_attentions=output_attentions,
|
1145 |
+
use_cache=use_cache,
|
1146 |
+
is_mem=is_mem,
|
1147 |
+
last_section_mask=last_section_mask,
|
1148 |
+
offload_cache_to_cpu=offload_cache_to_cpu,
|
1149 |
+
)
|
1150 |
+
|
1151 |
+
hidden_states = layer_outputs[0]
|
1152 |
+
|
1153 |
+
if use_cache:
|
1154 |
+
next_decoder_cache += (layer_outputs[2 if output_attentions else 1],)
|
1155 |
+
|
1156 |
+
if output_attentions:
|
1157 |
+
all_self_attns += (layer_outputs[1],)
|
1158 |
+
|
1159 |
+
hidden_states = self.norm(hidden_states)
|
1160 |
+
|
1161 |
+
# add hidden states from the last decoder layer
|
1162 |
+
if output_hidden_states:
|
1163 |
+
all_hidden_states += (hidden_states,)
|
1164 |
+
|
1165 |
+
next_cache = next_decoder_cache if use_cache else None
|
1166 |
+
if not return_dict:
|
1167 |
+
return tuple(
|
1168 |
+
v
|
1169 |
+
for v in [hidden_states, next_cache, all_hidden_states, all_self_attns]
|
1170 |
+
if v is not None
|
1171 |
+
)
|
1172 |
+
return BaseModelOutputWithPast(
|
1173 |
+
last_hidden_state=hidden_states,
|
1174 |
+
past_key_values=next_cache,
|
1175 |
+
hidden_states=all_hidden_states,
|
1176 |
+
attentions=all_self_attns,
|
1177 |
+
)
|
1178 |
+
|
1179 |
+
|
1180 |
+
class LlamaForCausalLM(LlamaPreTrainedModel):
|
1181 |
+
def __init__(self, config):
|
1182 |
+
super().__init__(config)
|
1183 |
+
self.model = LlamaModel(config)
|
1184 |
+
|
1185 |
+
self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
|
1186 |
+
|
1187 |
+
self.mem_id = None
|
1188 |
+
self.mem_freq = None
|
1189 |
+
self.top_k = None
|
1190 |
+
self.max_seq_len = None
|
1191 |
+
|
1192 |
+
# Initialize weights and apply final processing
|
1193 |
+
self.post_init()
|
1194 |
+
|
1195 |
+
def get_input_embeddings(self):
|
1196 |
+
return self.model.embed_tokens
|
1197 |
+
|
1198 |
+
def set_input_embeddings(self, value):
|
1199 |
+
self.model.embed_tokens = value
|
1200 |
+
|
1201 |
+
def get_output_embeddings(self):
|
1202 |
+
return self.lm_head
|
1203 |
+
|
1204 |
+
def set_output_embeddings(self, new_embeddings):
|
1205 |
+
self.lm_head = new_embeddings
|
1206 |
+
|
1207 |
+
def set_decoder(self, decoder):
|
1208 |
+
self.model = decoder
|
1209 |
+
|
1210 |
+
def get_decoder(self):
|
1211 |
+
return self.model
|
1212 |
+
|
1213 |
+
@add_start_docstrings_to_model_forward(LLAMA_INPUTS_DOCSTRING)
|
1214 |
+
@replace_return_docstrings(
|
1215 |
+
output_type=CausalLMOutputWithPast, config_class=_CONFIG_FOR_DOC
|
1216 |
+
)
|
1217 |
+
def forward(
|
1218 |
+
self,
|
1219 |
+
input_ids: torch.LongTensor = None,
|
1220 |
+
attention_mask: Optional[torch.Tensor] = None,
|
1221 |
+
position_ids: Optional[torch.LongTensor] = None,
|
1222 |
+
past_key_values: Optional[List[torch.FloatTensor]] = None,
|
1223 |
+
inputs_embeds: Optional[torch.FloatTensor] = None,
|
1224 |
+
labels: Optional[torch.LongTensor] = None,
|
1225 |
+
use_cache: Optional[bool] = None,
|
1226 |
+
output_attentions: Optional[bool] = None,
|
1227 |
+
output_hidden_states: Optional[bool] = None,
|
1228 |
+
return_dict: Optional[bool] = None,
|
1229 |
+
offload_cache_to_cpu: Optional[bool] = None,
|
1230 |
+
) -> Union[Tuple, CausalLMOutputWithPast]:
|
1231 |
+
r"""
|
1232 |
+
Args:
|
1233 |
+
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
|
1234 |
+
Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
|
1235 |
+
config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
|
1236 |
+
(masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.
|
1237 |
+
|
1238 |
+
Returns:
|
1239 |
+
|
1240 |
+
Example:
|
1241 |
+
|
1242 |
+
```python
|
1243 |
+
>>> from transformers import AutoTokenizer, LlamaForCausalLM
|
1244 |
+
|
1245 |
+
>>> model = LlamaForCausalLM.from_pretrained(PATH_TO_CONVERTED_WEIGHTS)
|
1246 |
+
>>> tokenizer = AutoTokenizer.from_pretrained(PATH_TO_CONVERTED_TOKENIZER)
|
1247 |
+
|
1248 |
+
>>> prompt = "Hey, are you consciours? Can you talk to me?"
|
1249 |
+
>>> inputs = tokenizer(prompt, return_tensors="pt")
|
1250 |
+
|
1251 |
+
>>> # Generate
|
1252 |
+
>>> generate_ids = model.generate(inputs.input_ids, max_length=30)
|
1253 |
+
>>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
|
1254 |
+
"Hey, are you consciours? Can you talk to me?\nI'm not consciours, but I can talk to you."
|
1255 |
+
```"""
|
1256 |
+
|
1257 |
+
output_attentions = (
|
1258 |
+
output_attentions
|
1259 |
+
if output_attentions is not None
|
1260 |
+
else self.config.output_attentions
|
1261 |
+
)
|
1262 |
+
output_hidden_states = (
|
1263 |
+
output_hidden_states
|
1264 |
+
if output_hidden_states is not None
|
1265 |
+
else self.config.output_hidden_states
|
1266 |
+
)
|
1267 |
+
return_dict = (
|
1268 |
+
return_dict if return_dict is not None else self.config.use_return_dict
|
1269 |
+
)
|
1270 |
+
|
1271 |
+
# decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn)
|
1272 |
+
window_len = self.max_seq_len or input_ids.shape[1]
|
1273 |
+
last_logits = None
|
1274 |
+
for _, idx in enumerate(range(0, input_ids.shape[1], window_len)):
|
1275 |
+
if idx >= 1:
|
1276 |
+
if output_attentions or output_hidden_states:
|
1277 |
+
raise NotImplementedError
|
1278 |
+
if not use_cache:
|
1279 |
+
raise NotImplementedError
|
1280 |
+
outputs = self.model(
|
1281 |
+
input_ids=input_ids[:, idx : idx + window_len],
|
1282 |
+
attention_mask=attention_mask[
|
1283 |
+
:, : idx + window_len + attention_mask.shape[1] - input_ids.shape[1]
|
1284 |
+
]
|
1285 |
+
if attention_mask is not None
|
1286 |
+
else None,
|
1287 |
+
position_ids=position_ids[:, idx : idx + window_len]
|
1288 |
+
if position_ids is not None
|
1289 |
+
else None,
|
1290 |
+
past_key_values=past_key_values,
|
1291 |
+
inputs_embeds=inputs_embeds[:, idx : idx + window_len]
|
1292 |
+
if inputs_embeds is not None
|
1293 |
+
else None,
|
1294 |
+
use_cache=use_cache,
|
1295 |
+
output_attentions=output_attentions,
|
1296 |
+
output_hidden_states=output_hidden_states,
|
1297 |
+
return_dict=return_dict,
|
1298 |
+
offload_cache_to_cpu=offload_cache_to_cpu,
|
1299 |
+
)
|
1300 |
+
past_key_values = outputs.past_key_values
|
1301 |
+
if last_logits is not None:
|
1302 |
+
last_logits = torch.cat((last_logits, outputs[0]), dim=-2)
|
1303 |
+
last_logits = outputs[0]
|
1304 |
+
|
1305 |
+
hidden_states = last_logits
|
1306 |
+
logits = self.lm_head(hidden_states)
|
1307 |
+
|
1308 |
+
loss = None
|
1309 |
+
if labels is not None:
|
1310 |
+
# Shift so that tokens < n predict n
|
1311 |
+
shift_logits = logits[..., :-1, :].contiguous()
|
1312 |
+
shift_labels = labels[..., 1:].contiguous()
|
1313 |
+
# Flatten the tokens
|
1314 |
+
loss_fct = CrossEntropyLoss()
|
1315 |
+
shift_logits = shift_logits.view(-1, self.config.vocab_size)
|
1316 |
+
shift_labels = shift_labels.view(-1)
|
1317 |
+
# Enable model parallelism
|
1318 |
+
shift_labels = shift_labels.to(shift_logits.device)
|
1319 |
+
loss = loss_fct(shift_logits, shift_labels)
|
1320 |
+
|
1321 |
+
if not return_dict:
|
1322 |
+
output = (logits,) + outputs[1:]
|
1323 |
+
return (loss,) + output if loss is not None else output
|
1324 |
+
|
1325 |
+
return CausalLMOutputWithPast(
|
1326 |
+
loss=loss,
|
1327 |
+
logits=logits,
|
1328 |
+
past_key_values=outputs.past_key_values,
|
1329 |
+
hidden_states=outputs.hidden_states,
|
1330 |
+
attentions=outputs.attentions,
|
1331 |
+
)
|
1332 |
+
|
1333 |
+
def set_mem_id(self, mem_id):
|
1334 |
+
self.mem_id = mem_id
|
1335 |
+
self.model.set_mem_id(mem_id)
|
1336 |
+
|
1337 |
+
def set_mem_cache_args(self, max_seq_len, mem_freq, top_k, max_cache_size):
|
1338 |
+
self.mem_freq = mem_freq
|
1339 |
+
self.top_k = top_k
|
1340 |
+
self.max_seq_len = max_seq_len
|
1341 |
+
if self.max_seq_len is not None:
|
1342 |
+
assert self.max_seq_len % (self.mem_freq + 1) == 0
|
1343 |
+
self.model.set_mem_cache_args(mem_freq, top_k, max_cache_size)
|
1344 |
+
|
1345 |
+
def prepare_inputs_for_generation(
|
1346 |
+
self,
|
1347 |
+
input_ids,
|
1348 |
+
past_key_values=None,
|
1349 |
+
attention_mask=None,
|
1350 |
+
inputs_embeds=None,
|
1351 |
+
**kwargs,
|
1352 |
+
):
|
1353 |
+
total_len = input_ids.shape[1]
|
1354 |
+
if past_key_values:
|
1355 |
+
prev_len = input_ids.shape[1] - 1
|
1356 |
+
else:
|
1357 |
+
prev_len = 0
|
1358 |
+
|
1359 |
+
position_ids = kwargs.get("position_ids", None)
|
1360 |
+
|
1361 |
+
if self.mem_freq is not None:
|
1362 |
+
if position_ids is not None:
|
1363 |
+
raise NotImplementedError
|
1364 |
+
# T = input_ids.shape[1]
|
1365 |
+
|
1366 |
+
prev_incomplete_len = prev_len % self.mem_freq
|
1367 |
+
prev_complete_len = prev_len - prev_incomplete_len
|
1368 |
+
incomplete_len = total_len % self.mem_freq
|
1369 |
+
new_full_len = total_len - prev_complete_len - incomplete_len
|
1370 |
+
|
1371 |
+
prev_input, input_ids_with_mem, input_ids_without_mem = torch.split(
|
1372 |
+
input_ids, (prev_complete_len, new_full_len, incomplete_len), dim=-1
|
1373 |
+
)
|
1374 |
+
|
1375 |
+
bsz, _ = input_ids.size()
|
1376 |
+
input_ids_with_mem = input_ids_with_mem.view(bsz, -1, self.mem_freq)
|
1377 |
+
input_ids_with_mem = torch.cat(
|
1378 |
+
(
|
1379 |
+
input_ids_with_mem,
|
1380 |
+
input_ids_with_mem.new_full(
|
1381 |
+
(bsz, input_ids_with_mem.shape[1], 1), self.mem_id
|
1382 |
+
),
|
1383 |
+
),
|
1384 |
+
dim=-1,
|
1385 |
+
).view(bsz, -1)
|
1386 |
+
input_ids = torch.cat(
|
1387 |
+
(prev_input, input_ids_with_mem, input_ids_without_mem), dim=-1
|
1388 |
+
)
|
1389 |
+
if attention_mask is not None:
|
1390 |
+
attention_mask_with_mem, attention_mask_without_mem = torch.split(
|
1391 |
+
attention_mask,
|
1392 |
+
(prev_complete_len + new_full_len, incomplete_len),
|
1393 |
+
dim=-1,
|
1394 |
+
)
|
1395 |
+
attention_mask_with_mem = attention_mask_with_mem.view(
|
1396 |
+
bsz, -1, self.mem_freq
|
1397 |
+
)
|
1398 |
+
attention_mask_with_mem = torch.cat(
|
1399 |
+
(
|
1400 |
+
attention_mask_with_mem,
|
1401 |
+
attention_mask_with_mem.new_ones(
|
1402 |
+
(bsz, attention_mask_with_mem.shape[1], 1)
|
1403 |
+
),
|
1404 |
+
),
|
1405 |
+
dim=-1,
|
1406 |
+
).view(bsz, -1)
|
1407 |
+
attention_mask = torch.cat(
|
1408 |
+
(attention_mask_with_mem, attention_mask_without_mem), dim=-1
|
1409 |
+
)
|
1410 |
+
|
1411 |
+
input_ids = input_ids[:, prev_len:]
|
1412 |
+
if attention_mask is not None and position_ids is None:
|
1413 |
+
# create position_ids on the fly for batch generation
|
1414 |
+
position_ids = attention_mask.long().cumsum(-1) - 1
|
1415 |
+
position_ids.masked_fill_(attention_mask == 0, 1)
|
1416 |
+
position_ids = position_ids[:, -input_ids.shape[1] :].unsqueeze(-1)
|
1417 |
+
|
1418 |
+
# if `inputs_embeds` are passed, we only want to use them in the 1st generation step
|
1419 |
+
if (
|
1420 |
+
inputs_embeds is not None
|
1421 |
+
and past_key_values is None
|
1422 |
+
and self.mem_freq is None
|
1423 |
+
):
|
1424 |
+
model_inputs = {"inputs_embeds": inputs_embeds}
|
1425 |
+
else:
|
1426 |
+
model_inputs = {"input_ids": input_ids}
|
1427 |
+
|
1428 |
+
model_inputs.update(
|
1429 |
+
{
|
1430 |
+
"position_ids": position_ids,
|
1431 |
+
"past_key_values": past_key_values,
|
1432 |
+
"use_cache": kwargs.get("use_cache"),
|
1433 |
+
"attention_mask": attention_mask,
|
1434 |
+
"offload_cache_to_cpu": kwargs.get("offload_cache_to_cpu"),
|
1435 |
+
}
|
1436 |
+
)
|
1437 |
+
return model_inputs
|
1438 |
+
|
1439 |
+
@staticmethod
|
1440 |
+
def _reorder_cache(past_key_values, beam_idx):
|
1441 |
+
reordered_past = ()
|
1442 |
+
for layer_past in past_key_values:
|
1443 |
+
reordered_past += (
|
1444 |
+
tuple(
|
1445 |
+
past_state.index_select(0, beam_idx) for past_state in layer_past
|
1446 |
+
),
|
1447 |
+
)
|
1448 |
+
return reordered_past
|
1449 |
+
|
1450 |
+
|
1451 |
+
@add_start_docstrings(
|
1452 |
+
"""
|
1453 |
+
The LLaMa Model transformer with a sequence classification head on top (linear layer).
|
1454 |
+
|
1455 |
+
[`LlamaForSequenceClassification`] uses the last token in order to do the classification, as other causal models
|
1456 |
+
(e.g. GPT-2) do.
|
1457 |
+
|
1458 |
+
Since it does classification on the last token, it requires to know the position of the last token. If a
|
1459 |
+
`pad_token_id` is defined in the configuration, it finds the last token that is not a padding token in each row. If
|
1460 |
+
no `pad_token_id` is defined, it simply takes the last value in each row of the batch. Since it cannot guess the
|
1461 |
+
padding tokens when `inputs_embeds` are passed instead of `input_ids`, it does the same (take the last value in
|
1462 |
+
each row of the batch).
|
1463 |
+
""",
|
1464 |
+
LLAMA_START_DOCSTRING,
|
1465 |
+
)
|
1466 |
+
class LlamaForSequenceClassification(LlamaPreTrainedModel):
|
1467 |
+
_keys_to_ignore_on_load_missing = [r"lm_head.weight"]
|
1468 |
+
|
1469 |
+
def __init__(self, config):
|
1470 |
+
super().__init__(config)
|
1471 |
+
self.num_labels = config.num_labels
|
1472 |
+
self.model = LlamaModel(config)
|
1473 |
+
self.score = nn.Linear(config.hidden_size, self.num_labels, bias=False)
|
1474 |
+
|
1475 |
+
# Initialize weights and apply final processing
|
1476 |
+
self.post_init()
|
1477 |
+
|
1478 |
+
def get_input_embeddings(self):
|
1479 |
+
return self.model.embed_tokens
|
1480 |
+
|
1481 |
+
def set_input_embeddings(self, value):
|
1482 |
+
self.model.embed_tokens = value
|
1483 |
+
|
1484 |
+
@add_start_docstrings_to_model_forward(LLAMA_INPUTS_DOCSTRING)
|
1485 |
+
def forward(
|
1486 |
+
self,
|
1487 |
+
input_ids: torch.LongTensor = None,
|
1488 |
+
attention_mask: Optional[torch.Tensor] = None,
|
1489 |
+
position_ids: Optional[torch.LongTensor] = None,
|
1490 |
+
past_key_values: Optional[List[torch.FloatTensor]] = None,
|
1491 |
+
inputs_embeds: Optional[torch.FloatTensor] = None,
|
1492 |
+
labels: Optional[torch.LongTensor] = None,
|
1493 |
+
use_cache: Optional[bool] = None,
|
1494 |
+
output_attentions: Optional[bool] = None,
|
1495 |
+
output_hidden_states: Optional[bool] = None,
|
1496 |
+
return_dict: Optional[bool] = None,
|
1497 |
+
) -> Union[Tuple, SequenceClassifierOutputWithPast]:
|
1498 |
+
r"""
|
1499 |
+
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
|
1500 |
+
Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
|
1501 |
+
config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
|
1502 |
+
`config.num_labels > 1` a classification loss is computed (Cross-Entropy).
|
1503 |
+
"""
|
1504 |
+
return_dict = (
|
1505 |
+
return_dict if return_dict is not None else self.config.use_return_dict
|
1506 |
+
)
|
1507 |
+
|
1508 |
+
transformer_outputs = self.model(
|
1509 |
+
input_ids,
|
1510 |
+
attention_mask=attention_mask,
|
1511 |
+
position_ids=position_ids,
|
1512 |
+
past_key_values=past_key_values,
|
1513 |
+
inputs_embeds=inputs_embeds,
|
1514 |
+
use_cache=use_cache,
|
1515 |
+
output_attentions=output_attentions,
|
1516 |
+
output_hidden_states=output_hidden_states,
|
1517 |
+
return_dict=return_dict,
|
1518 |
+
)
|
1519 |
+
hidden_states = transformer_outputs[0]
|
1520 |
+
logits = self.score(hidden_states)
|
1521 |
+
|
1522 |
+
if input_ids is not None:
|
1523 |
+
batch_size = input_ids.shape[0]
|
1524 |
+
else:
|
1525 |
+
batch_size = inputs_embeds.shape[0]
|
1526 |
+
|
1527 |
+
if self.config.pad_token_id is None and batch_size != 1:
|
1528 |
+
raise ValueError(
|
1529 |
+
"Cannot handle batch sizes > 1 if no padding token is defined."
|
1530 |
+
)
|
1531 |
+
if self.config.pad_token_id is None:
|
1532 |
+
sequence_lengths = -1
|
1533 |
+
else:
|
1534 |
+
if input_ids is not None:
|
1535 |
+
sequence_lengths = (
|
1536 |
+
torch.ne(input_ids, self.config.pad_token_id).sum(-1) - 1
|
1537 |
+
).to(logits.device)
|
1538 |
+
else:
|
1539 |
+
sequence_lengths = -1
|
1540 |
+
|
1541 |
+
pooled_logits = logits[
|
1542 |
+
torch.arange(batch_size, device=logits.device), sequence_lengths
|
1543 |
+
]
|
1544 |
+
|
1545 |
+
loss = None
|
1546 |
+
if labels is not None:
|
1547 |
+
labels = labels.to(logits.device)
|
1548 |
+
if self.config.problem_type is None:
|
1549 |
+
if self.num_labels == 1:
|
1550 |
+
self.config.problem_type = "regression"
|
1551 |
+
elif self.num_labels > 1 and (
|
1552 |
+
labels.dtype == torch.long or labels.dtype == torch.int
|
1553 |
+
):
|
1554 |
+
self.config.problem_type = "single_label_classification"
|
1555 |
+
else:
|
1556 |
+
self.config.problem_type = "multi_label_classification"
|
1557 |
+
|
1558 |
+
if self.config.problem_type == "regression":
|
1559 |
+
loss_fct = MSELoss()
|
1560 |
+
if self.num_labels == 1:
|
1561 |
+
loss = loss_fct(pooled_logits.squeeze(), labels.squeeze())
|
1562 |
+
else:
|
1563 |
+
loss = loss_fct(pooled_logits, labels)
|
1564 |
+
elif self.config.problem_type == "single_label_classification":
|
1565 |
+
loss_fct = CrossEntropyLoss()
|
1566 |
+
loss = loss_fct(
|
1567 |
+
pooled_logits.view(-1, self.num_labels), labels.view(-1)
|
1568 |
+
)
|
1569 |
+
elif self.config.problem_type == "multi_label_classification":
|
1570 |
+
loss_fct = BCEWithLogitsLoss()
|
1571 |
+
loss = loss_fct(pooled_logits, labels)
|
1572 |
+
if not return_dict:
|
1573 |
+
output = (pooled_logits,) + transformer_outputs[1:]
|
1574 |
+
return ((loss,) + output) if loss is not None else output
|
1575 |
+
|
1576 |
+
return SequenceClassifierOutputWithPast(
|
1577 |
+
loss=loss,
|
1578 |
+
logits=pooled_logits,
|
1579 |
+
past_key_values=transformer_outputs.past_key_values,
|
1580 |
+
hidden_states=transformer_outputs.hidden_states,
|
1581 |
+
attentions=transformer_outputs.attentions,
|
1582 |
+
)
|
1583 |
+
|
1584 |
+
|
1585 |
+
def add_mem_tokens(example, mem_freq, mem_id):
|
1586 |
+
x = example["input_ids"]
|
1587 |
+
ret = []
|
1588 |
+
prev_idx = 0
|
1589 |
+
for t_idx in range(mem_freq, len(x), mem_freq):
|
1590 |
+
ret.extend(x[prev_idx:t_idx])
|
1591 |
+
ret.append(mem_id)
|
1592 |
+
prev_idx = t_idx
|
1593 |
+
ret.extend(x[prev_idx:])
|
1594 |
+
# drop attention_mask
|
1595 |
+
return {"input_ids": ret}
|
src/axolotl/utils/models.py
CHANGED
@@ -20,7 +20,9 @@ from transformers import ( # noqa: F401
|
|
20 |
)
|
21 |
|
22 |
try:
|
23 |
-
from transformers import
|
|
|
|
|
24 |
except ImportError:
|
25 |
logging.warning(
|
26 |
"This version of transformers does not support Llama. Consider upgrading."
|
@@ -83,37 +85,47 @@ def load_model(
|
|
83 |
adapter="lora",
|
84 |
inference=False,
|
85 |
):
|
86 |
-
# type: (str, str, str,
|
87 |
"""
|
88 |
Load a model from a base model and a model type.
|
89 |
"""
|
90 |
|
91 |
# TODO refactor as a kwarg
|
92 |
load_in_8bit = cfg.load_in_8bit
|
93 |
-
is_llama_derived_model = "llama" in base_model or (
|
94 |
cfg.model_type and "llama" in cfg.model_type.lower()
|
95 |
)
|
96 |
|
97 |
-
if is_llama_derived_model and cfg.flash_attention:
|
98 |
if cfg.device not in ["mps", "cpu"] and inference is False:
|
99 |
from axolotl.flash_attn import replace_llama_attn_with_flash_attn
|
100 |
|
101 |
logging.info("patching with flash attention")
|
102 |
replace_llama_attn_with_flash_attn()
|
103 |
-
elif is_llama_derived_model and cfg.xformers_attention:
|
104 |
from axolotl.monkeypatch.llama_attn_hijack_xformers import (
|
105 |
hijack_llama_attention,
|
106 |
)
|
107 |
|
108 |
logging.info("patching with xformers attention")
|
109 |
hijack_llama_attention()
|
110 |
-
elif is_llama_derived_model and cfg.sdp_attention:
|
111 |
from axolotl.monkeypatch.llama_attn_hijack_xformers import (
|
112 |
hijack_llama_sdp_attention,
|
113 |
)
|
114 |
|
115 |
logging.info("patching with sdp attention")
|
116 |
hijack_llama_sdp_attention()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
117 |
|
118 |
if cfg.bf16:
|
119 |
torch_dtype = torch.bfloat16
|
@@ -145,7 +157,7 @@ def load_model(
|
|
145 |
bnb_4bit_quant_type="nf4",
|
146 |
)
|
147 |
try:
|
148 |
-
if cfg.gptq and is_llama_derived_model:
|
149 |
from alpaca_lora_4bit.autograd_4bit import load_llama_model_4bit_low_ram
|
150 |
from huggingface_hub import snapshot_download
|
151 |
|
@@ -183,7 +195,7 @@ def load_model(
|
|
183 |
else True,
|
184 |
)
|
185 |
load_in_8bit = False
|
186 |
-
elif is_llama_derived_model and "LlamaForCausalLM" in globals():
|
187 |
config = LlamaConfig.from_pretrained(base_model_config)
|
188 |
model = LlamaForCausalLM.from_pretrained(
|
189 |
base_model,
|
|
|
20 |
)
|
21 |
|
22 |
try:
|
23 |
+
from transformers import ( # pylint: disable=unused-import # noqa: F401
|
24 |
+
LlamaForCausalLM,
|
25 |
+
)
|
26 |
except ImportError:
|
27 |
logging.warning(
|
28 |
"This version of transformers does not support Llama. Consider upgrading."
|
|
|
85 |
adapter="lora",
|
86 |
inference=False,
|
87 |
):
|
88 |
+
# type: (str, str, str, AutoTokenizer, DictDefault, Optional[str], bool) -> Tuple[PreTrainedModel, Optional[PeftConfig]]
|
89 |
"""
|
90 |
Load a model from a base model and a model type.
|
91 |
"""
|
92 |
|
93 |
# TODO refactor as a kwarg
|
94 |
load_in_8bit = cfg.load_in_8bit
|
95 |
+
cfg.is_llama_derived_model = "llama" in base_model or (
|
96 |
cfg.model_type and "llama" in cfg.model_type.lower()
|
97 |
)
|
98 |
|
99 |
+
if cfg.is_llama_derived_model and cfg.flash_attention:
|
100 |
if cfg.device not in ["mps", "cpu"] and inference is False:
|
101 |
from axolotl.flash_attn import replace_llama_attn_with_flash_attn
|
102 |
|
103 |
logging.info("patching with flash attention")
|
104 |
replace_llama_attn_with_flash_attn()
|
105 |
+
elif cfg.is_llama_derived_model and cfg.xformers_attention:
|
106 |
from axolotl.monkeypatch.llama_attn_hijack_xformers import (
|
107 |
hijack_llama_attention,
|
108 |
)
|
109 |
|
110 |
logging.info("patching with xformers attention")
|
111 |
hijack_llama_attention()
|
112 |
+
elif cfg.is_llama_derived_model and cfg.sdp_attention:
|
113 |
from axolotl.monkeypatch.llama_attn_hijack_xformers import (
|
114 |
hijack_llama_sdp_attention,
|
115 |
)
|
116 |
|
117 |
logging.info("patching with sdp attention")
|
118 |
hijack_llama_sdp_attention()
|
119 |
+
elif cfg.is_llama_derived_model and cfg.landmark_attention:
|
120 |
+
from axolotl.monkeypatch.llama_landmark_attn import ( # pylint: disable=redefined-outer-name # noqa: F811
|
121 |
+
MEM_TOKEN,
|
122 |
+
LlamaForCausalLM,
|
123 |
+
)
|
124 |
+
|
125 |
+
logging.info("patching with landmark attention")
|
126 |
+
|
127 |
+
# TODO: Check if this would overwrite previous additional_special_tokens
|
128 |
+
tokenizer.add_special_tokens({"additional_special_tokens": [MEM_TOKEN]})
|
129 |
|
130 |
if cfg.bf16:
|
131 |
torch_dtype = torch.bfloat16
|
|
|
157 |
bnb_4bit_quant_type="nf4",
|
158 |
)
|
159 |
try:
|
160 |
+
if cfg.gptq and cfg.is_llama_derived_model:
|
161 |
from alpaca_lora_4bit.autograd_4bit import load_llama_model_4bit_low_ram
|
162 |
from huggingface_hub import snapshot_download
|
163 |
|
|
|
195 |
else True,
|
196 |
)
|
197 |
load_in_8bit = False
|
198 |
+
elif cfg.is_llama_derived_model and "LlamaForCausalLM" in globals():
|
199 |
config = LlamaConfig.from_pretrained(base_model_config)
|
200 |
model = LlamaForCausalLM.from_pretrained(
|
201 |
base_model,
|
src/axolotl/utils/trainer.py
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
"""Module containing the Trainer class and related functions"""
|
2 |
|
3 |
import importlib
|
|
|
4 |
import math
|
5 |
import os
|
6 |
import sys
|
@@ -235,6 +236,23 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer):
|
|
235 |
else:
|
236 |
data_collator_kwargs["pad_to_multiple_of"] = 8
|
237 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
238 |
trainer_cls = (
|
239 |
OneCycleLRSchedulerTrainer
|
240 |
if cfg.lr_scheduler == "one_cycle" and (cfg.fsdp or cfg.adapter == "qlora")
|
|
|
1 |
"""Module containing the Trainer class and related functions"""
|
2 |
|
3 |
import importlib
|
4 |
+
import logging
|
5 |
import math
|
6 |
import os
|
7 |
import sys
|
|
|
236 |
else:
|
237 |
data_collator_kwargs["pad_to_multiple_of"] = 8
|
238 |
|
239 |
+
if cfg.is_llama_derived_model and cfg.landmark_attention:
|
240 |
+
from functools import partial
|
241 |
+
|
242 |
+
from axolotl.monkeypatch.llama_landmark_attn import MEM_TOKEN, add_mem_tokens
|
243 |
+
|
244 |
+
mem_id = tokenizer.convert_tokens_to_ids(MEM_TOKEN)
|
245 |
+
model.set_mem_id(mem_id)
|
246 |
+
|
247 |
+
logging.info("Adding landmark attention tokens to dataset")
|
248 |
+
|
249 |
+
for dataset in [train_dataset, eval_dataset]:
|
250 |
+
dataset = dataset.map(
|
251 |
+
partial(add_mem_tokens, mem_freq=50, mem_id=mem_id),
|
252 |
+
batched=False,
|
253 |
+
num_proc=32,
|
254 |
+
)
|
255 |
+
|
256 |
trainer_cls = (
|
257 |
OneCycleLRSchedulerTrainer
|
258 |
if cfg.lr_scheduler == "one_cycle" and (cfg.fsdp or cfg.adapter == "qlora")
|