SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Large modular logic refactoring (#34487)

Browse Source 
* rework converter

* Update modular_model_converter.py

* Update modular_model_converter.py

* Update modular_model_converter.py

* Update modular_model_converter.py

* cleaning

* cleaning

* finalize imports

* imports

* Update modular_model_converter.py

* Better renaming to avoid visiting same file multiple times

* start converting files

* style

* address most comments

* style

* remove unused stuff in get_needed_imports

* style

* move class dependency functions outside class

* Move main functions outside class

* style

* Update modular_model_converter.py

* rename func

* add augmented dependencies

* Update modular_model_converter.py

* Add types_to_file_type + tweak annotation handling

* Allow assignment dependency mapping + fix regex

* style + update modular examples

* fix modular_roberta example (wrong redefinition of __init__)

* slightly correct order in which dependencies will appear

* style

* review comments

* Performance + better handling of dependencies when they are imported

* style

* Add advanced new classes capabilities

* style

* add forgotten check

* Update modeling_llava_next_video.py

* Add prority list ordering in check_conversion as well

* Update check_modular_conversion.py

* Update configuration_gemma.py
This commit is contained in:
Cyril Vallez
2024-11-01 10:13:51 +01:00
committed by GitHub
parent 86701f2b6f
commit e2ac16b28a
19 changed files with 2726 additions and 1658 deletions
Download Patch File Download Diff File Expand all files Collapse all files

190
examples/modular-transformers/modeling_dummy_bert.py
View File

@@ -1,27 +1,20 @@
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# This file was automatically generated from <path_to_modular_file.py>.
# Do NOT edit this file manually as any edits will be overwritten by the generation of
# the file from the modular. If any change should be done, please apply the change to the
# modular_xxx.py file directly. One of our CI enforces this
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# This file was automatically generated from examples/modular-transformers/modular_dummy_bert.py.
# Do NOT edit this file manually as any edits will be overwritten by the generation of
# the file from the modular. If any change should be done, please apply the change to the
# modular_dummy_bert.py file directly. One of our CI enforces this.
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
import math
import os
from typing import List, Optional, Tuple, Union
import torch
import torch.utils.checkpoint
from packaging import version
from torch import nn
from ...activations import ACT2FN
from ...modeling_attn_mask_utils import (
_prepare_4d_attention_mask_for_sdpa,
_prepare_4d_causal_attention_mask_for_sdpa,
)
from ...modeling_outputs import (
BaseModelOutputWithPastAndCrossAttentions,
BaseModelOutputWithPoolingAndCrossAttentions,
)
from ...modeling_attn_mask_utils import _prepare_4d_attention_mask_for_sdpa, _prepare_4d_causal_attention_mask_for_sdpa
from ...modeling_outputs import BaseModelOutputWithPastAndCrossAttentions, BaseModelOutputWithPoolingAndCrossAttentions
from ...modeling_utils import PreTrainedModel
from ...pytorch_utils import apply_chunking_to_forward, find_pruneable_heads_and_indices, prune_linear_layer
from ...utils import (
@@ -40,79 +33,6 @@ _CHECKPOINT_FOR_DOC = "google-dummy_bert/dummy_bert-base-uncased"
_CONFIG_FOR_DOC = "DummyBertConfig"
def load_tf_weights_in_dummy_bert(model, config, tf_checkpoint_path):
"""Load tf checkpoints in a pytorch model."""
try:
import re
import numpy as np
import tensorflow as tf
except ImportError:
logger.error(
"Loading a TensorFlow model in PyTorch, requires TensorFlow to be installed. Please see "
"https://www.tensorflow.org/install/ for installation instructions."
)
raise
tf_path = os.path.abspath(tf_checkpoint_path)
logger.info(f"Converting TensorFlow checkpoint from {tf_path}")
# Load weights from TF model
init_vars = tf.train.list_variables(tf_path)
names = []
arrays = []
for name, shape in init_vars:
logger.info(f"Loading TF weight {name} with shape {shape}")
array = tf.train.load_variable(tf_path, name)
names.append(name)
arrays.append(array)
for name, array in zip(names, arrays):
name = name.split("/")
# adam_v and adam_m are variables used in AdamWeightDecayOptimizer to calculated m and v
# which are not required for using pretrained model
if any(
n in ["adam_v", "adam_m", "AdamWeightDecayOptimizer", "AdamWeightDecayOptimizer_1", "global_step"]
for n in name
):
logger.info(f"Skipping {'/'.join(name)}")
continue
pointer = model
for m_name in name:
if re.fullmatch(r"[A-Za-z]+_\d+", m_name):
scope_names = re.split(r"_(\d+)", m_name)
else:
scope_names = [m_name]
if scope_names[0] == "kernel" or scope_names[0] == "gamma":
pointer = getattr(pointer, "weight")
elif scope_names[0] == "output_bias" or scope_names[0] == "beta":
pointer = getattr(pointer, "bias")
elif scope_names[0] == "output_weights":
pointer = getattr(pointer, "weight")
elif scope_names[0] == "squad":
pointer = getattr(pointer, "classifier")
else:
try:
pointer = getattr(pointer, scope_names[0])
except AttributeError:
logger.info(f"Skipping {'/'.join(name)}")
continue
if len(scope_names) >= 2:
num = int(scope_names[1])
pointer = pointer[num]
if m_name[-11:] == "_embeddings":
pointer = getattr(pointer, "weight")
elif m_name == "kernel":
array = np.transpose(array)
try:
if pointer.shape != array.shape:
raise ValueError(f"Pointer shape {pointer.shape} and array shape {array.shape} mismatched")
except ValueError as e:
e.args += (pointer.shape, array.shape)
raise
logger.info(f"Initialize PyTorch weight {name}")
pointer.data = torch.from_numpy(array)
return model
class DummyBertEmbeddings(nn.Module):
"""Construct the embeddings from word, position and token_type embeddings."""
@@ -706,6 +626,79 @@ class DummyBertPooler(nn.Module):
return pooled_output
def load_tf_weights_in_dummy_bert(model, config, tf_checkpoint_path):
"""Load tf checkpoints in a pytorch model."""
try:
import re
import numpy as np
import tensorflow as tf
except ImportError:
logger.error(
"Loading a TensorFlow model in PyTorch, requires TensorFlow to be installed. Please see "
"https://www.tensorflow.org/install/ for installation instructions."
)
raise
tf_path = os.path.abspath(tf_checkpoint_path)
logger.info(f"Converting TensorFlow checkpoint from {tf_path}")
# Load weights from TF model
init_vars = tf.train.list_variables(tf_path)
names = []
arrays = []
for name, shape in init_vars:
logger.info(f"Loading TF weight {name} with shape {shape}")
array = tf.train.load_variable(tf_path, name)
names.append(name)
arrays.append(array)
for name, array in zip(names, arrays):
name = name.split("/")
# adam_v and adam_m are variables used in AdamWeightDecayOptimizer to calculated m and v
# which are not required for using pretrained model
if any(
n in ["adam_v", "adam_m", "AdamWeightDecayOptimizer", "AdamWeightDecayOptimizer_1", "global_step"]
for n in name
):
logger.info(f"Skipping {'/'.join(name)}")
continue
pointer = model
for m_name in name:
if re.fullmatch(r"[A-Za-z]+_\d+", m_name):
scope_names = re.split(r"_(\d+)", m_name)
else:
scope_names = [m_name]
if scope_names[0] == "kernel" or scope_names[0] == "gamma":
pointer = getattr(pointer, "weight")
elif scope_names[0] == "output_bias" or scope_names[0] == "beta":
pointer = getattr(pointer, "bias")
elif scope_names[0] == "output_weights":
pointer = getattr(pointer, "weight")
elif scope_names[0] == "squad":
pointer = getattr(pointer, "classifier")
else:
try:
pointer = getattr(pointer, scope_names[0])
except AttributeError:
logger.info(f"Skipping {'/'.join(name)}")
continue
if len(scope_names) >= 2:
num = int(scope_names[1])
pointer = pointer[num]
if m_name[-11:] == "_embeddings":
pointer = getattr(pointer, "weight")
elif m_name == "kernel":
array = np.transpose(array)
try:
if pointer.shape != array.shape:
raise ValueError(f"Pointer shape {pointer.shape} and array shape {array.shape} mismatched")
except ValueError as e:
e.args += (pointer.shape, array.shape)
raise
logger.info(f"Initialize PyTorch weight {name}")
pointer.data = torch.from_numpy(array)
return model
class DummyBertPreTrainedModel(PreTrainedModel):
"""
An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained
@@ -871,26 +864,6 @@ class DummyBertModel(DummyBertPreTrainedModel):
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[Tuple[torch.Tensor], BaseModelOutputWithPoolingAndCrossAttentions]:
r"""
encoder_hidden_states (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if
the model is configured as a decoder.
encoder_attention_mask (`torch.FloatTensor` of shape `(batch_size, sequence_length)` or `(batch_size, sequence_length, target_length)`, *optional*):
Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:
- 1 for tokens that are **not masked**,
- 0 for tokens that are **masked**.
past_key_values (`tuple(tuple(torch.FloatTensor))` of length `config.n_layers` with each tuple having 4 tensors of shape `(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):
Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding.
If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that
don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of all
`decoder_input_ids` of shape `(batch_size, sequence_length)`.
use_cache (`bool`, *optional*):
If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
`past_key_values`).
"""
r"""
encoder_hidden_states (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if
@@ -1027,7 +1000,6 @@ class DummyBertModel(DummyBertPreTrainedModel):
if not return_dict:
return (sequence_output, pooled_output) + encoder_outputs[1:]
return super().forward(input_ids)
return BaseModelOutputWithPoolingAndCrossAttentions(
last_hidden_state=sequence_output,