File size: 11,410 Bytes
3f96a16 881b143 3f96a16 |
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 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 |
"""Converts Huggingface Causal LM to Prefix LM.
Conversion does lightweight surgery on a HuggingFace
Causal LM to convert it to a Prefix LM.
Prefix LMs accepts a `bidirectional_mask` input in `forward`
and treat the input prompt as the prefix in `generate`.
"""
from types import MethodType
from typing import Any, List, MutableMapping, Optional, Tuple, Union
import torch
from transformers.models.gpt2.modeling_gpt2 import GPT2LMHeadModel
from transformers.models.gpt_neo.modeling_gpt_neo import GPTNeoForCausalLM
from transformers.models.gpt_neox.modeling_gpt_neox import GPTNeoXForCausalLM
from transformers.models.gptj.modeling_gptj import GPTJForCausalLM
_SUPPORTED_GPT_MODELS = (
GPT2LMHeadModel,
GPTJForCausalLM,
GPTNeoForCausalLM,
GPTNeoXForCausalLM,
)
CAUSAL_GPT_TYPES = Union[
GPT2LMHeadModel, GPTJForCausalLM, GPTNeoForCausalLM, GPTNeoXForCausalLM
]
def _convert_gpt_causal_lm_to_prefix_lm(model: CAUSAL_GPT_TYPES) -> CAUSAL_GPT_TYPES:
"""Converts a GPT-style Causal LM to a Prefix LM.
Supported HuggingFace model classes:
- `GPT2LMHeadModel`
- `GPTNeoForCausalLM`
- `GPTNeoXForCausalLM`
- `GPTJForCausalLM`
See `convert_hf_causal_lm_to_prefix_lm` for more details.
"""
if hasattr(model, "_prefix_lm_converted"):
return model
assert isinstance(model, _SUPPORTED_GPT_MODELS)
assert (
model.config.add_cross_attention == False
), "Only supports GPT-style decoder-only models"
def _get_attn_modules(model: CAUSAL_GPT_TYPES) -> List[torch.nn.Module]:
"""Helper that gets a list of the model's attention modules.
Each module has a `bias` buffer used for causal masking. The Prefix LM
conversion adds logic to dynamically manipulate these biases to support
Prefix LM attention masking.
"""
attn_modules = []
if isinstance(model, GPTNeoXForCausalLM):
blocks = model.gpt_neox.layers
else:
blocks = model.transformer.h
for block in blocks:
if isinstance(model, GPTNeoForCausalLM):
if block.attn.attention_type != "global":
continue
attn_module = block.attn.attention
elif isinstance(model, GPTNeoXForCausalLM):
attn_module = block.attention
else:
attn_module = block.attn
attn_modules.append(attn_module)
return attn_modules
setattr(model, "_original_forward", getattr(model, "forward"))
setattr(model, "_original_generate", getattr(model, "generate"))
def forward(
self: CAUSAL_GPT_TYPES,
input_ids: Optional[torch.LongTensor] = None,
past_key_values: Optional[Tuple[Tuple[torch.Tensor]]] = None,
attention_mask: Optional[torch.FloatTensor] = None,
bidirectional_mask: Optional[torch.Tensor] = None,
token_type_ids: Optional[torch.LongTensor] = None,
position_ids: Optional[torch.LongTensor] = None,
head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
labels: Optional[torch.LongTensor] = None,
use_cache: Optional[bool] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
):
"""Wraps original forward to enable PrefixLM attention."""
def call_og_forward():
if isinstance(self, GPTNeoXForCausalLM):
return self._original_forward(
input_ids=input_ids,
past_key_values=past_key_values,
attention_mask=attention_mask,
head_mask=head_mask,
inputs_embeds=inputs_embeds,
labels=labels,
use_cache=use_cache,
output_attentions=output_attentions,
output_hidden_states=output_hidden_states,
return_dict=return_dict,
)
else:
return self._original_forward(
input_ids=input_ids,
past_key_values=past_key_values,
attention_mask=attention_mask,
token_type_ids=token_type_ids,
position_ids=position_ids,
head_mask=head_mask,
inputs_embeds=inputs_embeds,
labels=labels,
use_cache=use_cache,
output_attentions=output_attentions,
output_hidden_states=output_hidden_states,
return_dict=return_dict,
)
if bidirectional_mask is None:
return call_og_forward()
assert isinstance(bidirectional_mask, torch.Tensor)
attn_modules = _get_attn_modules(model)
(b, s) = bidirectional_mask.shape
max_length = attn_modules[0].bias.shape[-1]
if s > max_length:
raise ValueError(
f"bidirectional_mask sequence length (={s}) exceeds the "
+ f"max length allowed by the model ({max_length})."
)
assert s <= max_length
if s < max_length:
pad = torch.zeros(
(int(b), int(max_length - s)),
dtype=bidirectional_mask.dtype,
device=bidirectional_mask.device,
)
bidirectional_mask = torch.cat([bidirectional_mask, pad], dim=1)
bidirectional = bidirectional_mask.unsqueeze(1).unsqueeze(1)
for attn_module in attn_modules:
assert isinstance(attn_module.bias, torch.Tensor)
attn_module.bias.data = torch.logical_or(
attn_module.bias.data, bidirectional
)
output = call_og_forward()
for attn_module in attn_modules:
attn_module.bias.data = torch.tril(attn_module.bias.data[0, 0])[None, None]
return output
def generate(self: CAUSAL_GPT_TYPES, *args: Any, **kwargs: Any):
"""Wraps original generate to enable PrefixLM attention."""
attn_modules = _get_attn_modules(model)
for attn_module in attn_modules:
attn_module.bias.data[:] = 1
output = self._original_generate(*args, **kwargs)
for attn_module in attn_modules:
attn_module.bias.data = torch.tril(attn_module.bias.data[0, 0])[None, None]
return output
setattr(model, "forward", MethodType(forward, model))
setattr(model, "generate", MethodType(generate, model))
setattr(model, "_prefix_lm_converted", True)
return model
_SUPPORTED_HF_MODELS = _SUPPORTED_GPT_MODELS
CAUSAL_LM_TYPES = Union[
GPT2LMHeadModel, GPTJForCausalLM, GPTNeoForCausalLM, GPTNeoXForCausalLM
]
def convert_hf_causal_lm_to_prefix_lm(model: CAUSAL_LM_TYPES) -> CAUSAL_LM_TYPES:
"""Converts a HuggingFace Causal LM to a Prefix LM.
Supported HuggingFace model classes:
- `GPT2LMHeadModel`
- `GPTNeoForCausalLM`
- `GPTNeoXForCausalLM`
- `GPTJForCausalLM`
Conversion to a Prefix LM is done by modifying the `forward` method, and possibly also the
`generate` method and/or select underlying methods depending on the model class.
These changes preserve the model API, but add a new input to `forward`: "bidirectional_mask".
Notes on training:
To actually train the converted model as a Prefix LM, training batches will need to indicate
the prefix/target structure by including `bidirectional_mask` as part of the batch inputs.
**This is not a standard input and requires custom layers either within or after your dataloader.**
In addition to adding `bidirectional_mask` to the batch, this custom code should modify `labels`
such that `batch['labels'][batch['bidirectional_mask'] == 1] == -100`.
That is, the prefix portion of the sequence should not generate any loss. Loss should only be
generated by the target portion of the sequence.
Notes on `GPTNeoForCausalLM`:
To simplify the implementation, "global" and "local" attention layers are handled differently.
For "global" layers, we handle conversion as described above. For "local" layers, which use a
causal attention mask within a restricted local window, we do not alter the masking.
Notes on `forward` method conversion:
After conversion, the `forward` method will handle a new input, `bidirectional_mask`,
which should be a [batch_size, seq_length] byte tensor, where 1 indicates token positions
belonging to the prefix (prefix tokens can attend to one another bidirectionally), and
0 indicates token positions belonging to the target.
The new `forward` method will incorporate `bidirectional_mask` (if supplied) into the existing
causal mask, call the original `forward` method, and (if the causal mask is a buffer) reset
the causal masks before returning the result.
Notes on `generate` method conversion:
After conversion, the `generate` method will have the same signature but will internally
convert all causal masks to be purely bidirectional, call the original `generate` method, and
(where appropriate) reset the causal masks before returning the result.
This works thanks to the logic of the HuggingFace `generate` API, which first encodes the token
"prompt" passed to `generate` (which is treated as the prefix) and then sequentially generates
each new token. Encodings are cached as generation happens, so all prefix tokens can attend to one
another (as expected in a Prefix LM) and generated tokens can only attend to prefix tokens and
previously-generated tokens (also as expected in a Prefix LM).
To preserve the API, the original methods are renamed to `_original_forward` and
`_original_generate`, and replaced with new `forward` and `generate` methods that wrap
them, respectively. Although implementation details vary by model class.
"""
if isinstance(model, _SUPPORTED_GPT_MODELS):
return _convert_gpt_causal_lm_to_prefix_lm(model)
else:
raise TypeError(
f"Cannot convert model to Prefix LM. "
+ f"Model does not belong to set of supported HF models:"
+ f"\n{_SUPPORTED_HF_MODELS}"
)
def add_bidirectional_mask_if_missing(batch: MutableMapping):
"""Attempts to add bidirectional_mask to batch if missing.
Raises:
KeyError if bidirectional_mask is missing and can't be inferred
"""
if "bidirectional_mask" not in batch:
if batch.get("mode", None) == "icl_task":
batch["bidirectional_mask"] = batch["attention_mask"].clone()
for i, continuation_indices in enumerate(batch["continuation_indices"]):
batch["bidirectional_mask"][i, continuation_indices] = 0
elif "labels" in batch and "attention_mask" in batch:
batch["bidirectional_mask"] = torch.logical_and(
torch.eq(batch["attention_mask"], 1), torch.eq(batch["labels"], -100)
).type_as(batch["attention_mask"])
else:
raise KeyError(
"No bidirectional_mask in batch and not sure how to construct one."
)
|