Refactor: Move some code to the comfy/text_encoders folder.
This commit is contained in:
comfyanonymous
@@ -1,12 +1,12 @@
|
||||
from comfy import sd1_clip
|
||||
from .llama_tokenizer import LLAMATokenizer
|
||||
import comfy.t5
|
||||
import comfy.text_encoders.t5
|
||||
import os
|
||||
|
||||
class PT5XlModel(sd1_clip.SDClipModel):
|
||||
def __init__(self, device="cpu", layer="last", layer_idx=None, dtype=None):
|
||||
textmodel_json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "t5_pile_config_xl.json")
|
||||
super().__init__(device=device, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, dtype=dtype, special_tokens={"end": 2, "pad": 1}, model_class=comfy.t5.T5, enable_attention_masks=True, zero_out_masked=True)
|
||||
super().__init__(device=device, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, dtype=dtype, special_tokens={"end": 2, "pad": 1}, model_class=comfy.text_encoders.t5.T5, enable_attention_masks=True, zero_out_masked=True)
|
||||
|
||||
class PT5XlTokenizer(sd1_clip.SDTokenizer):
|
||||
def __init__(self, embedding_directory=None):
|
||||
|
||||
22
comfy/text_encoders/sa_t5.py
Normal file
22
comfy/text_encoders/sa_t5.py
Normal file
@@ -0,0 +1,22 @@
|
||||
from comfy import sd1_clip
|
||||
from transformers import T5TokenizerFast
|
||||
import comfy.text_encoders.t5
|
||||
import os
|
||||
|
||||
class T5BaseModel(sd1_clip.SDClipModel):
|
||||
def __init__(self, device="cpu", layer="last", layer_idx=None, dtype=None):
|
||||
textmodel_json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "t5_config_base.json")
|
||||
super().__init__(device=device, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, dtype=dtype, special_tokens={"end": 1, "pad": 0}, model_class=comfy.text_encoders.t5.T5, enable_attention_masks=True, zero_out_masked=True)
|
||||
|
||||
class T5BaseTokenizer(sd1_clip.SDTokenizer):
|
||||
def __init__(self, embedding_directory=None):
|
||||
tokenizer_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), "t5_tokenizer")
|
||||
super().__init__(tokenizer_path, pad_with_end=False, embedding_size=768, embedding_key='t5base', tokenizer_class=T5TokenizerFast, has_start_token=False, pad_to_max_length=False, max_length=99999999, min_length=128)
|
||||
|
||||
class SAT5Tokenizer(sd1_clip.SD1Tokenizer):
|
||||
def __init__(self, embedding_directory=None):
|
||||
super().__init__(embedding_directory=embedding_directory, clip_name="t5base", tokenizer=T5BaseTokenizer)
|
||||
|
||||
class SAT5Model(sd1_clip.SD1ClipModel):
|
||||
def __init__(self, device="cpu", dtype=None, **kwargs):
|
||||
super().__init__(device=device, dtype=dtype, name="t5base", clip_model=T5BaseModel, **kwargs)
|
||||
150
comfy/text_encoders/sd3_clip.py
Normal file
150
comfy/text_encoders/sd3_clip.py
Normal file
@@ -0,0 +1,150 @@
|
||||
from comfy import sd1_clip
|
||||
from comfy import sdxl_clip
|
||||
from transformers import T5TokenizerFast
|
||||
import comfy.text_encoders.t5
|
||||
import torch
|
||||
import os
|
||||
import comfy.model_management
|
||||
import logging
|
||||
|
||||
class T5XXLModel(sd1_clip.SDClipModel):
|
||||
def __init__(self, device="cpu", layer="last", layer_idx=None, dtype=None):
|
||||
textmodel_json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "t5_config_xxl.json")
|
||||
super().__init__(device=device, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, dtype=dtype, special_tokens={"end": 1, "pad": 0}, model_class=comfy.text_encoders.t5.T5)
|
||||
|
||||
class T5XXLTokenizer(sd1_clip.SDTokenizer):
|
||||
def __init__(self, embedding_directory=None):
|
||||
tokenizer_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), "t5_tokenizer")
|
||||
super().__init__(tokenizer_path, pad_with_end=False, embedding_size=4096, embedding_key='t5xxl', tokenizer_class=T5TokenizerFast, has_start_token=False, pad_to_max_length=False, max_length=99999999, min_length=77)
|
||||
|
||||
class SDT5XXLTokenizer(sd1_clip.SD1Tokenizer):
|
||||
def __init__(self, embedding_directory=None):
|
||||
super().__init__(embedding_directory=embedding_directory, clip_name="t5xxl", tokenizer=T5XXLTokenizer)
|
||||
|
||||
class SDT5XXLModel(sd1_clip.SD1ClipModel):
|
||||
def __init__(self, device="cpu", dtype=None, **kwargs):
|
||||
super().__init__(device=device, dtype=dtype, clip_name="t5xxl", clip_model=T5XXLModel, **kwargs)
|
||||
|
||||
|
||||
|
||||
class SD3Tokenizer:
|
||||
def __init__(self, embedding_directory=None):
|
||||
self.clip_l = sd1_clip.SDTokenizer(embedding_directory=embedding_directory)
|
||||
self.clip_g = sdxl_clip.SDXLClipGTokenizer(embedding_directory=embedding_directory)
|
||||
self.t5xxl = T5XXLTokenizer(embedding_directory=embedding_directory)
|
||||
|
||||
def tokenize_with_weights(self, text:str, return_word_ids=False):
|
||||
out = {}
|
||||
out["g"] = self.clip_g.tokenize_with_weights(text, return_word_ids)
|
||||
out["l"] = self.clip_l.tokenize_with_weights(text, return_word_ids)
|
||||
out["t5xxl"] = self.t5xxl.tokenize_with_weights(text, return_word_ids)
|
||||
return out
|
||||
|
||||
def untokenize(self, token_weight_pair):
|
||||
return self.clip_g.untokenize(token_weight_pair)
|
||||
|
||||
class SD3ClipModel(torch.nn.Module):
|
||||
def __init__(self, clip_l=True, clip_g=True, t5=True, dtype_t5=None, device="cpu", dtype=None):
|
||||
super().__init__()
|
||||
self.dtypes = set()
|
||||
if clip_l:
|
||||
self.clip_l = sd1_clip.SDClipModel(layer="hidden", layer_idx=-2, device=device, dtype=dtype, layer_norm_hidden_state=False, return_projected_pooled=False)
|
||||
self.dtypes.add(dtype)
|
||||
else:
|
||||
self.clip_l = None
|
||||
|
||||
if clip_g:
|
||||
self.clip_g = sdxl_clip.SDXLClipG(device=device, dtype=dtype)
|
||||
self.dtypes.add(dtype)
|
||||
else:
|
||||
self.clip_g = None
|
||||
|
||||
if t5:
|
||||
if dtype_t5 is None:
|
||||
dtype_t5 = dtype
|
||||
elif comfy.model_management.dtype_size(dtype_t5) > comfy.model_management.dtype_size(dtype):
|
||||
dtype_t5 = dtype
|
||||
|
||||
if not comfy.model_management.supports_cast(device, dtype_t5):
|
||||
dtype_t5 = dtype
|
||||
|
||||
self.t5xxl = T5XXLModel(device=device, dtype=dtype_t5)
|
||||
self.dtypes.add(dtype_t5)
|
||||
else:
|
||||
self.t5xxl = None
|
||||
|
||||
logging.debug("Created SD3 text encoder with: clip_l {}, clip_g {}, t5xxl {}:{}".format(clip_l, clip_g, t5, dtype_t5))
|
||||
|
||||
def set_clip_options(self, options):
|
||||
if self.clip_l is not None:
|
||||
self.clip_l.set_clip_options(options)
|
||||
if self.clip_g is not None:
|
||||
self.clip_g.set_clip_options(options)
|
||||
if self.t5xxl is not None:
|
||||
self.t5xxl.set_clip_options(options)
|
||||
|
||||
def reset_clip_options(self):
|
||||
if self.clip_l is not None:
|
||||
self.clip_l.reset_clip_options()
|
||||
if self.clip_g is not None:
|
||||
self.clip_g.reset_clip_options()
|
||||
if self.t5xxl is not None:
|
||||
self.t5xxl.reset_clip_options()
|
||||
|
||||
def encode_token_weights(self, token_weight_pairs):
|
||||
token_weight_pairs_l = token_weight_pairs["l"]
|
||||
token_weight_pairs_g = token_weight_pairs["g"]
|
||||
token_weight_pars_t5 = token_weight_pairs["t5xxl"]
|
||||
lg_out = None
|
||||
pooled = None
|
||||
out = None
|
||||
|
||||
if len(token_weight_pairs_g) > 0 or len(token_weight_pairs_l) > 0:
|
||||
if self.clip_l is not None:
|
||||
lg_out, l_pooled = self.clip_l.encode_token_weights(token_weight_pairs_l)
|
||||
else:
|
||||
l_pooled = torch.zeros((1, 768), device=comfy.model_management.intermediate_device())
|
||||
|
||||
if self.clip_g is not None:
|
||||
g_out, g_pooled = self.clip_g.encode_token_weights(token_weight_pairs_g)
|
||||
if lg_out is not None:
|
||||
lg_out = torch.cat([lg_out, g_out], dim=-1)
|
||||
else:
|
||||
lg_out = torch.nn.functional.pad(g_out, (768, 0))
|
||||
else:
|
||||
g_out = None
|
||||
g_pooled = torch.zeros((1, 1280), device=comfy.model_management.intermediate_device())
|
||||
|
||||
if lg_out is not None:
|
||||
lg_out = torch.nn.functional.pad(lg_out, (0, 4096 - lg_out.shape[-1]))
|
||||
out = lg_out
|
||||
pooled = torch.cat((l_pooled, g_pooled), dim=-1)
|
||||
|
||||
if self.t5xxl is not None:
|
||||
t5_out, t5_pooled = self.t5xxl.encode_token_weights(token_weight_pars_t5)
|
||||
if lg_out is not None:
|
||||
out = torch.cat([lg_out, t5_out], dim=-2)
|
||||
else:
|
||||
out = t5_out
|
||||
|
||||
if out is None:
|
||||
out = torch.zeros((1, 77, 4096), device=comfy.model_management.intermediate_device())
|
||||
|
||||
if pooled is None:
|
||||
pooled = torch.zeros((1, 768 + 1280), device=comfy.model_management.intermediate_device())
|
||||
|
||||
return out, pooled
|
||||
|
||||
def load_sd(self, sd):
|
||||
if "text_model.encoder.layers.30.mlp.fc1.weight" in sd:
|
||||
return self.clip_g.load_sd(sd)
|
||||
elif "text_model.encoder.layers.1.mlp.fc1.weight" in sd:
|
||||
return self.clip_l.load_sd(sd)
|
||||
else:
|
||||
return self.t5xxl.load_sd(sd)
|
||||
|
||||
def sd3_clip(clip_l=True, clip_g=True, t5=True, dtype_t5=None):
|
||||
class SD3ClipModel_(SD3ClipModel):
|
||||
def __init__(self, device="cpu", dtype=None):
|
||||
super().__init__(clip_l=clip_l, clip_g=clip_g, t5=t5, dtype_t5=dtype_t5, device=device, dtype=dtype)
|
||||
return SD3ClipModel_
|
||||
238
comfy/text_encoders/t5.py
Normal file
238
comfy/text_encoders/t5.py
Normal file
@@ -0,0 +1,238 @@
|
||||
import torch
|
||||
import math
|
||||
from comfy.ldm.modules.attention import optimized_attention_for_device
|
||||
|
||||
class T5LayerNorm(torch.nn.Module):
|
||||
def __init__(self, hidden_size, eps=1e-6, dtype=None, device=None, operations=None):
|
||||
super().__init__()
|
||||
self.weight = torch.nn.Parameter(torch.empty(hidden_size, dtype=dtype, device=device))
|
||||
self.variance_epsilon = eps
|
||||
|
||||
def forward(self, x):
|
||||
variance = x.pow(2).mean(-1, keepdim=True)
|
||||
x = x * torch.rsqrt(variance + self.variance_epsilon)
|
||||
return self.weight.to(device=x.device, dtype=x.dtype) * x
|
||||
|
||||
activations = {
|
||||
"gelu_pytorch_tanh": lambda a: torch.nn.functional.gelu(a, approximate="tanh"),
|
||||
"relu": torch.nn.functional.relu,
|
||||
}
|
||||
|
||||
class T5DenseActDense(torch.nn.Module):
|
||||
def __init__(self, model_dim, ff_dim, ff_activation, dtype, device, operations):
|
||||
super().__init__()
|
||||
self.wi = operations.Linear(model_dim, ff_dim, bias=False, dtype=dtype, device=device)
|
||||
self.wo = operations.Linear(ff_dim, model_dim, bias=False, dtype=dtype, device=device)
|
||||
# self.dropout = nn.Dropout(config.dropout_rate)
|
||||
self.act = activations[ff_activation]
|
||||
|
||||
def forward(self, x):
|
||||
x = self.act(self.wi(x))
|
||||
# x = self.dropout(x)
|
||||
x = self.wo(x)
|
||||
return x
|
||||
|
||||
class T5DenseGatedActDense(torch.nn.Module):
|
||||
def __init__(self, model_dim, ff_dim, ff_activation, dtype, device, operations):
|
||||
super().__init__()
|
||||
self.wi_0 = operations.Linear(model_dim, ff_dim, bias=False, dtype=dtype, device=device)
|
||||
self.wi_1 = operations.Linear(model_dim, ff_dim, bias=False, dtype=dtype, device=device)
|
||||
self.wo = operations.Linear(ff_dim, model_dim, bias=False, dtype=dtype, device=device)
|
||||
# self.dropout = nn.Dropout(config.dropout_rate)
|
||||
self.act = activations[ff_activation]
|
||||
|
||||
def forward(self, x):
|
||||
hidden_gelu = self.act(self.wi_0(x))
|
||||
hidden_linear = self.wi_1(x)
|
||||
x = hidden_gelu * hidden_linear
|
||||
# x = self.dropout(x)
|
||||
x = self.wo(x)
|
||||
return x
|
||||
|
||||
class T5LayerFF(torch.nn.Module):
|
||||
def __init__(self, model_dim, ff_dim, ff_activation, gated_act, dtype, device, operations):
|
||||
super().__init__()
|
||||
if gated_act:
|
||||
self.DenseReluDense = T5DenseGatedActDense(model_dim, ff_dim, ff_activation, dtype, device, operations)
|
||||
else:
|
||||
self.DenseReluDense = T5DenseActDense(model_dim, ff_dim, ff_activation, dtype, device, operations)
|
||||
|
||||
self.layer_norm = T5LayerNorm(model_dim, dtype=dtype, device=device, operations=operations)
|
||||
# self.dropout = nn.Dropout(config.dropout_rate)
|
||||
|
||||
def forward(self, x):
|
||||
forwarded_states = self.layer_norm(x)
|
||||
forwarded_states = self.DenseReluDense(forwarded_states)
|
||||
# x = x + self.dropout(forwarded_states)
|
||||
x += forwarded_states
|
||||
return x
|
||||
|
||||
class T5Attention(torch.nn.Module):
|
||||
def __init__(self, model_dim, inner_dim, num_heads, relative_attention_bias, dtype, device, operations):
|
||||
super().__init__()
|
||||
|
||||
# Mesh TensorFlow initialization to avoid scaling before softmax
|
||||
self.q = operations.Linear(model_dim, inner_dim, bias=False, dtype=dtype, device=device)
|
||||
self.k = operations.Linear(model_dim, inner_dim, bias=False, dtype=dtype, device=device)
|
||||
self.v = operations.Linear(model_dim, inner_dim, bias=False, dtype=dtype, device=device)
|
||||
self.o = operations.Linear(inner_dim, model_dim, bias=False, dtype=dtype, device=device)
|
||||
self.num_heads = num_heads
|
||||
|
||||
self.relative_attention_bias = None
|
||||
if relative_attention_bias:
|
||||
self.relative_attention_num_buckets = 32
|
||||
self.relative_attention_max_distance = 128
|
||||
self.relative_attention_bias = torch.nn.Embedding(self.relative_attention_num_buckets, self.num_heads, device=device)
|
||||
|
||||
@staticmethod
|
||||
def _relative_position_bucket(relative_position, bidirectional=True, num_buckets=32, max_distance=128):
|
||||
"""
|
||||
Adapted from Mesh Tensorflow:
|
||||
https://github.com/tensorflow/mesh/blob/0cb87fe07da627bf0b7e60475d59f95ed6b5be3d/mesh_tensorflow/transformer/transformer_layers.py#L593
|
||||
|
||||
Translate relative position to a bucket number for relative attention. The relative position is defined as
|
||||
memory_position - query_position, i.e. the distance in tokens from the attending position to the attended-to
|
||||
position. If bidirectional=False, then positive relative positions are invalid. We use smaller buckets for
|
||||
small absolute relative_position and larger buckets for larger absolute relative_positions. All relative
|
||||
positions >=max_distance map to the same bucket. All relative positions <=-max_distance map to the same bucket.
|
||||
This should allow for more graceful generalization to longer sequences than the model has been trained on
|
||||
|
||||
Args:
|
||||
relative_position: an int32 Tensor
|
||||
bidirectional: a boolean - whether the attention is bidirectional
|
||||
num_buckets: an integer
|
||||
max_distance: an integer
|
||||
|
||||
Returns:
|
||||
a Tensor with the same shape as relative_position, containing int32 values in the range [0, num_buckets)
|
||||
"""
|
||||
relative_buckets = 0
|
||||
if bidirectional:
|
||||
num_buckets //= 2
|
||||
relative_buckets += (relative_position > 0).to(torch.long) * num_buckets
|
||||
relative_position = torch.abs(relative_position)
|
||||
else:
|
||||
relative_position = -torch.min(relative_position, torch.zeros_like(relative_position))
|
||||
# now relative_position is in the range [0, inf)
|
||||
|
||||
# half of the buckets are for exact increments in positions
|
||||
max_exact = num_buckets // 2
|
||||
is_small = relative_position < max_exact
|
||||
|
||||
# The other half of the buckets are for logarithmically bigger bins in positions up to max_distance
|
||||
relative_position_if_large = max_exact + (
|
||||
torch.log(relative_position.float() / max_exact)
|
||||
/ math.log(max_distance / max_exact)
|
||||
* (num_buckets - max_exact)
|
||||
).to(torch.long)
|
||||
relative_position_if_large = torch.min(
|
||||
relative_position_if_large, torch.full_like(relative_position_if_large, num_buckets - 1)
|
||||
)
|
||||
|
||||
relative_buckets += torch.where(is_small, relative_position, relative_position_if_large)
|
||||
return relative_buckets
|
||||
|
||||
def compute_bias(self, query_length, key_length, device):
|
||||
"""Compute binned relative position bias"""
|
||||
context_position = torch.arange(query_length, dtype=torch.long, device=device)[:, None]
|
||||
memory_position = torch.arange(key_length, dtype=torch.long, device=device)[None, :]
|
||||
relative_position = memory_position - context_position # shape (query_length, key_length)
|
||||
relative_position_bucket = self._relative_position_bucket(
|
||||
relative_position, # shape (query_length, key_length)
|
||||
bidirectional=True,
|
||||
num_buckets=self.relative_attention_num_buckets,
|
||||
max_distance=self.relative_attention_max_distance,
|
||||
)
|
||||
values = self.relative_attention_bias(relative_position_bucket) # shape (query_length, key_length, num_heads)
|
||||
values = values.permute([2, 0, 1]).unsqueeze(0) # shape (1, num_heads, query_length, key_length)
|
||||
return values
|
||||
|
||||
def forward(self, x, mask=None, past_bias=None, optimized_attention=None):
|
||||
q = self.q(x)
|
||||
k = self.k(x)
|
||||
v = self.v(x)
|
||||
if self.relative_attention_bias is not None:
|
||||
past_bias = self.compute_bias(x.shape[1], x.shape[1], x.device)
|
||||
|
||||
if past_bias is not None:
|
||||
if mask is not None:
|
||||
mask = mask + past_bias
|
||||
else:
|
||||
mask = past_bias
|
||||
|
||||
out = optimized_attention(q, k * ((k.shape[-1] / self.num_heads) ** 0.5), v, self.num_heads, mask)
|
||||
return self.o(out), past_bias
|
||||
|
||||
class T5LayerSelfAttention(torch.nn.Module):
|
||||
def __init__(self, model_dim, inner_dim, ff_dim, num_heads, relative_attention_bias, dtype, device, operations):
|
||||
super().__init__()
|
||||
self.SelfAttention = T5Attention(model_dim, inner_dim, num_heads, relative_attention_bias, dtype, device, operations)
|
||||
self.layer_norm = T5LayerNorm(model_dim, dtype=dtype, device=device, operations=operations)
|
||||
# self.dropout = nn.Dropout(config.dropout_rate)
|
||||
|
||||
def forward(self, x, mask=None, past_bias=None, optimized_attention=None):
|
||||
normed_hidden_states = self.layer_norm(x)
|
||||
output, past_bias = self.SelfAttention(self.layer_norm(x), mask=mask, past_bias=past_bias, optimized_attention=optimized_attention)
|
||||
# x = x + self.dropout(attention_output)
|
||||
x += output
|
||||
return x, past_bias
|
||||
|
||||
class T5Block(torch.nn.Module):
|
||||
def __init__(self, model_dim, inner_dim, ff_dim, ff_activation, gated_act, num_heads, relative_attention_bias, dtype, device, operations):
|
||||
super().__init__()
|
||||
self.layer = torch.nn.ModuleList()
|
||||
self.layer.append(T5LayerSelfAttention(model_dim, inner_dim, ff_dim, num_heads, relative_attention_bias, dtype, device, operations))
|
||||
self.layer.append(T5LayerFF(model_dim, ff_dim, ff_activation, gated_act, dtype, device, operations))
|
||||
|
||||
def forward(self, x, mask=None, past_bias=None, optimized_attention=None):
|
||||
x, past_bias = self.layer[0](x, mask, past_bias, optimized_attention)
|
||||
x = self.layer[-1](x)
|
||||
return x, past_bias
|
||||
|
||||
class T5Stack(torch.nn.Module):
|
||||
def __init__(self, num_layers, model_dim, inner_dim, ff_dim, ff_activation, gated_act, num_heads, relative_attention, dtype, device, operations):
|
||||
super().__init__()
|
||||
|
||||
self.block = torch.nn.ModuleList(
|
||||
[T5Block(model_dim, inner_dim, ff_dim, ff_activation, gated_act, num_heads, relative_attention_bias=((not relative_attention) or (i == 0)), dtype=dtype, device=device, operations=operations) for i in range(num_layers)]
|
||||
)
|
||||
self.final_layer_norm = T5LayerNorm(model_dim, dtype=dtype, device=device, operations=operations)
|
||||
# self.dropout = nn.Dropout(config.dropout_rate)
|
||||
|
||||
def forward(self, x, attention_mask=None, intermediate_output=None, final_layer_norm_intermediate=True):
|
||||
mask = None
|
||||
if attention_mask is not None:
|
||||
mask = 1.0 - attention_mask.to(x.dtype).reshape((attention_mask.shape[0], 1, -1, attention_mask.shape[-1])).expand(attention_mask.shape[0], 1, attention_mask.shape[-1], attention_mask.shape[-1])
|
||||
mask = mask.masked_fill(mask.to(torch.bool), float("-inf"))
|
||||
|
||||
intermediate = None
|
||||
optimized_attention = optimized_attention_for_device(x.device, mask=attention_mask is not None, small_input=True)
|
||||
past_bias = None
|
||||
for i, l in enumerate(self.block):
|
||||
x, past_bias = l(x, mask, past_bias, optimized_attention)
|
||||
if i == intermediate_output:
|
||||
intermediate = x.clone()
|
||||
x = self.final_layer_norm(x)
|
||||
if intermediate is not None and final_layer_norm_intermediate:
|
||||
intermediate = self.final_layer_norm(intermediate)
|
||||
return x, intermediate
|
||||
|
||||
class T5(torch.nn.Module):
|
||||
def __init__(self, config_dict, dtype, device, operations):
|
||||
super().__init__()
|
||||
self.num_layers = config_dict["num_layers"]
|
||||
model_dim = config_dict["d_model"]
|
||||
|
||||
self.encoder = T5Stack(self.num_layers, model_dim, model_dim, config_dict["d_ff"], config_dict["dense_act_fn"], config_dict["is_gated_act"], config_dict["num_heads"], config_dict["model_type"] == "t5", dtype, device, operations)
|
||||
self.dtype = dtype
|
||||
self.shared = torch.nn.Embedding(config_dict["vocab_size"], model_dim, device=device)
|
||||
|
||||
def get_input_embeddings(self):
|
||||
return self.shared
|
||||
|
||||
def set_input_embeddings(self, embeddings):
|
||||
self.shared = embeddings
|
||||
|
||||
def forward(self, input_ids, *args, **kwargs):
|
||||
x = self.shared(input_ids)
|
||||
return self.encoder(x, *args, **kwargs)
|
||||
22
comfy/text_encoders/t5_config_base.json
Normal file
22
comfy/text_encoders/t5_config_base.json
Normal file
@@ -0,0 +1,22 @@
|
||||
{
|
||||
"d_ff": 3072,
|
||||
"d_kv": 64,
|
||||
"d_model": 768,
|
||||
"decoder_start_token_id": 0,
|
||||
"dropout_rate": 0.1,
|
||||
"eos_token_id": 1,
|
||||
"dense_act_fn": "relu",
|
||||
"initializer_factor": 1.0,
|
||||
"is_encoder_decoder": true,
|
||||
"is_gated_act": false,
|
||||
"layer_norm_epsilon": 1e-06,
|
||||
"model_type": "t5",
|
||||
"num_decoder_layers": 12,
|
||||
"num_heads": 12,
|
||||
"num_layers": 12,
|
||||
"output_past": true,
|
||||
"pad_token_id": 0,
|
||||
"relative_attention_num_buckets": 32,
|
||||
"tie_word_embeddings": false,
|
||||
"vocab_size": 32128
|
||||
}
|
||||
22
comfy/text_encoders/t5_config_xxl.json
Normal file
22
comfy/text_encoders/t5_config_xxl.json
Normal file
@@ -0,0 +1,22 @@
|
||||
{
|
||||
"d_ff": 10240,
|
||||
"d_kv": 64,
|
||||
"d_model": 4096,
|
||||
"decoder_start_token_id": 0,
|
||||
"dropout_rate": 0.1,
|
||||
"eos_token_id": 1,
|
||||
"dense_act_fn": "gelu_pytorch_tanh",
|
||||
"initializer_factor": 1.0,
|
||||
"is_encoder_decoder": true,
|
||||
"is_gated_act": true,
|
||||
"layer_norm_epsilon": 1e-06,
|
||||
"model_type": "t5",
|
||||
"num_decoder_layers": 24,
|
||||
"num_heads": 64,
|
||||
"num_layers": 24,
|
||||
"output_past": true,
|
||||
"pad_token_id": 0,
|
||||
"relative_attention_num_buckets": 32,
|
||||
"tie_word_embeddings": false,
|
||||
"vocab_size": 32128
|
||||
}
|
||||
125
comfy/text_encoders/t5_tokenizer/special_tokens_map.json
Normal file
125
comfy/text_encoders/t5_tokenizer/special_tokens_map.json
Normal file
@@ -0,0 +1,125 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<extra_id_0>",
|
||||
"<extra_id_1>",
|
||||
"<extra_id_2>",
|
||||
"<extra_id_3>",
|
||||
"<extra_id_4>",
|
||||
"<extra_id_5>",
|
||||
"<extra_id_6>",
|
||||
"<extra_id_7>",
|
||||
"<extra_id_8>",
|
||||
"<extra_id_9>",
|
||||
"<extra_id_10>",
|
||||
"<extra_id_11>",
|
||||
"<extra_id_12>",
|
||||
"<extra_id_13>",
|
||||
"<extra_id_14>",
|
||||
"<extra_id_15>",
|
||||
"<extra_id_16>",
|
||||
"<extra_id_17>",
|
||||
"<extra_id_18>",
|
||||
"<extra_id_19>",
|
||||
"<extra_id_20>",
|
||||
"<extra_id_21>",
|
||||
"<extra_id_22>",
|
||||
"<extra_id_23>",
|
||||
"<extra_id_24>",
|
||||
"<extra_id_25>",
|
||||
"<extra_id_26>",
|
||||
"<extra_id_27>",
|
||||
"<extra_id_28>",
|
||||
"<extra_id_29>",
|
||||
"<extra_id_30>",
|
||||
"<extra_id_31>",
|
||||
"<extra_id_32>",
|
||||
"<extra_id_33>",
|
||||
"<extra_id_34>",
|
||||
"<extra_id_35>",
|
||||
"<extra_id_36>",
|
||||
"<extra_id_37>",
|
||||
"<extra_id_38>",
|
||||
"<extra_id_39>",
|
||||
"<extra_id_40>",
|
||||
"<extra_id_41>",
|
||||
"<extra_id_42>",
|
||||
"<extra_id_43>",
|
||||
"<extra_id_44>",
|
||||
"<extra_id_45>",
|
||||
"<extra_id_46>",
|
||||
"<extra_id_47>",
|
||||
"<extra_id_48>",
|
||||
"<extra_id_49>",
|
||||
"<extra_id_50>",
|
||||
"<extra_id_51>",
|
||||
"<extra_id_52>",
|
||||
"<extra_id_53>",
|
||||
"<extra_id_54>",
|
||||
"<extra_id_55>",
|
||||
"<extra_id_56>",
|
||||
"<extra_id_57>",
|
||||
"<extra_id_58>",
|
||||
"<extra_id_59>",
|
||||
"<extra_id_60>",
|
||||
"<extra_id_61>",
|
||||
"<extra_id_62>",
|
||||
"<extra_id_63>",
|
||||
"<extra_id_64>",
|
||||
"<extra_id_65>",
|
||||
"<extra_id_66>",
|
||||
"<extra_id_67>",
|
||||
"<extra_id_68>",
|
||||
"<extra_id_69>",
|
||||
"<extra_id_70>",
|
||||
"<extra_id_71>",
|
||||
"<extra_id_72>",
|
||||
"<extra_id_73>",
|
||||
"<extra_id_74>",
|
||||
"<extra_id_75>",
|
||||
"<extra_id_76>",
|
||||
"<extra_id_77>",
|
||||
"<extra_id_78>",
|
||||
"<extra_id_79>",
|
||||
"<extra_id_80>",
|
||||
"<extra_id_81>",
|
||||
"<extra_id_82>",
|
||||
"<extra_id_83>",
|
||||
"<extra_id_84>",
|
||||
"<extra_id_85>",
|
||||
"<extra_id_86>",
|
||||
"<extra_id_87>",
|
||||
"<extra_id_88>",
|
||||
"<extra_id_89>",
|
||||
"<extra_id_90>",
|
||||
"<extra_id_91>",
|
||||
"<extra_id_92>",
|
||||
"<extra_id_93>",
|
||||
"<extra_id_94>",
|
||||
"<extra_id_95>",
|
||||
"<extra_id_96>",
|
||||
"<extra_id_97>",
|
||||
"<extra_id_98>",
|
||||
"<extra_id_99>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
129428
comfy/text_encoders/t5_tokenizer/tokenizer.json
Normal file
129428
comfy/text_encoders/t5_tokenizer/tokenizer.json
Normal file
File diff suppressed because one or more lines are too long
939
comfy/text_encoders/t5_tokenizer/tokenizer_config.json
Normal file
939
comfy/text_encoders/t5_tokenizer/tokenizer_config.json
Normal file
@@ -0,0 +1,939 @@
|
||||
{
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32000": {
|
||||
"content": "<extra_id_99>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32001": {
|
||||
"content": "<extra_id_98>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32002": {
|
||||
"content": "<extra_id_97>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32003": {
|
||||
"content": "<extra_id_96>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32004": {
|
||||
"content": "<extra_id_95>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32005": {
|
||||
"content": "<extra_id_94>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32006": {
|
||||
"content": "<extra_id_93>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32007": {
|
||||
"content": "<extra_id_92>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32008": {
|
||||
"content": "<extra_id_91>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32009": {
|
||||
"content": "<extra_id_90>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32010": {
|
||||
"content": "<extra_id_89>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32011": {
|
||||
"content": "<extra_id_88>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32012": {
|
||||
"content": "<extra_id_87>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32013": {
|
||||
"content": "<extra_id_86>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32014": {
|
||||
"content": "<extra_id_85>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32015": {
|
||||
"content": "<extra_id_84>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32016": {
|
||||
"content": "<extra_id_83>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32017": {
|
||||
"content": "<extra_id_82>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32018": {
|
||||
"content": "<extra_id_81>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32019": {
|
||||
"content": "<extra_id_80>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32020": {
|
||||
"content": "<extra_id_79>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32021": {
|
||||
"content": "<extra_id_78>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32022": {
|
||||
"content": "<extra_id_77>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32023": {
|
||||
"content": "<extra_id_76>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32024": {
|
||||
"content": "<extra_id_75>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32025": {
|
||||
"content": "<extra_id_74>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32026": {
|
||||
"content": "<extra_id_73>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32027": {
|
||||
"content": "<extra_id_72>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32028": {
|
||||
"content": "<extra_id_71>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32029": {
|
||||
"content": "<extra_id_70>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32030": {
|
||||
"content": "<extra_id_69>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32031": {
|
||||
"content": "<extra_id_68>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32032": {
|
||||
"content": "<extra_id_67>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32033": {
|
||||
"content": "<extra_id_66>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32034": {
|
||||
"content": "<extra_id_65>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32035": {
|
||||
"content": "<extra_id_64>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32036": {
|
||||
"content": "<extra_id_63>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32037": {
|
||||
"content": "<extra_id_62>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32038": {
|
||||
"content": "<extra_id_61>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32039": {
|
||||
"content": "<extra_id_60>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32040": {
|
||||
"content": "<extra_id_59>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32041": {
|
||||
"content": "<extra_id_58>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32042": {
|
||||
"content": "<extra_id_57>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32043": {
|
||||
"content": "<extra_id_56>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32044": {
|
||||
"content": "<extra_id_55>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32045": {
|
||||
"content": "<extra_id_54>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32046": {
|
||||
"content": "<extra_id_53>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32047": {
|
||||
"content": "<extra_id_52>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32048": {
|
||||
"content": "<extra_id_51>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32049": {
|
||||
"content": "<extra_id_50>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32050": {
|
||||
"content": "<extra_id_49>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32051": {
|
||||
"content": "<extra_id_48>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32052": {
|
||||
"content": "<extra_id_47>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32053": {
|
||||
"content": "<extra_id_46>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32054": {
|
||||
"content": "<extra_id_45>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32055": {
|
||||
"content": "<extra_id_44>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32056": {
|
||||
"content": "<extra_id_43>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32057": {
|
||||
"content": "<extra_id_42>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32058": {
|
||||
"content": "<extra_id_41>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32059": {
|
||||
"content": "<extra_id_40>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32060": {
|
||||
"content": "<extra_id_39>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32061": {
|
||||
"content": "<extra_id_38>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32062": {
|
||||
"content": "<extra_id_37>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32063": {
|
||||
"content": "<extra_id_36>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32064": {
|
||||
"content": "<extra_id_35>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32065": {
|
||||
"content": "<extra_id_34>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32066": {
|
||||
"content": "<extra_id_33>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32067": {
|
||||
"content": "<extra_id_32>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32068": {
|
||||
"content": "<extra_id_31>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32069": {
|
||||
"content": "<extra_id_30>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32070": {
|
||||
"content": "<extra_id_29>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32071": {
|
||||
"content": "<extra_id_28>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32072": {
|
||||
"content": "<extra_id_27>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32073": {
|
||||
"content": "<extra_id_26>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32074": {
|
||||
"content": "<extra_id_25>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32075": {
|
||||
"content": "<extra_id_24>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32076": {
|
||||
"content": "<extra_id_23>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32077": {
|
||||
"content": "<extra_id_22>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32078": {
|
||||
"content": "<extra_id_21>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32079": {
|
||||
"content": "<extra_id_20>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32080": {
|
||||
"content": "<extra_id_19>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32081": {
|
||||
"content": "<extra_id_18>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32082": {
|
||||
"content": "<extra_id_17>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32083": {
|
||||
"content": "<extra_id_16>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32084": {
|
||||
"content": "<extra_id_15>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32085": {
|
||||
"content": "<extra_id_14>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32086": {
|
||||
"content": "<extra_id_13>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32087": {
|
||||
"content": "<extra_id_12>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32088": {
|
||||
"content": "<extra_id_11>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32089": {
|
||||
"content": "<extra_id_10>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32090": {
|
||||
"content": "<extra_id_9>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32091": {
|
||||
"content": "<extra_id_8>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32092": {
|
||||
"content": "<extra_id_7>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32093": {
|
||||
"content": "<extra_id_6>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32094": {
|
||||
"content": "<extra_id_5>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32095": {
|
||||
"content": "<extra_id_4>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32096": {
|
||||
"content": "<extra_id_3>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32097": {
|
||||
"content": "<extra_id_2>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32098": {
|
||||
"content": "<extra_id_1>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32099": {
|
||||
"content": "<extra_id_0>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<extra_id_0>",
|
||||
"<extra_id_1>",
|
||||
"<extra_id_2>",
|
||||
"<extra_id_3>",
|
||||
"<extra_id_4>",
|
||||
"<extra_id_5>",
|
||||
"<extra_id_6>",
|
||||
"<extra_id_7>",
|
||||
"<extra_id_8>",
|
||||
"<extra_id_9>",
|
||||
"<extra_id_10>",
|
||||
"<extra_id_11>",
|
||||
"<extra_id_12>",
|
||||
"<extra_id_13>",
|
||||
"<extra_id_14>",
|
||||
"<extra_id_15>",
|
||||
"<extra_id_16>",
|
||||
"<extra_id_17>",
|
||||
"<extra_id_18>",
|
||||
"<extra_id_19>",
|
||||
"<extra_id_20>",
|
||||
"<extra_id_21>",
|
||||
"<extra_id_22>",
|
||||
"<extra_id_23>",
|
||||
"<extra_id_24>",
|
||||
"<extra_id_25>",
|
||||
"<extra_id_26>",
|
||||
"<extra_id_27>",
|
||||
"<extra_id_28>",
|
||||
"<extra_id_29>",
|
||||
"<extra_id_30>",
|
||||
"<extra_id_31>",
|
||||
"<extra_id_32>",
|
||||
"<extra_id_33>",
|
||||
"<extra_id_34>",
|
||||
"<extra_id_35>",
|
||||
"<extra_id_36>",
|
||||
"<extra_id_37>",
|
||||
"<extra_id_38>",
|
||||
"<extra_id_39>",
|
||||
"<extra_id_40>",
|
||||
"<extra_id_41>",
|
||||
"<extra_id_42>",
|
||||
"<extra_id_43>",
|
||||
"<extra_id_44>",
|
||||
"<extra_id_45>",
|
||||
"<extra_id_46>",
|
||||
"<extra_id_47>",
|
||||
"<extra_id_48>",
|
||||
"<extra_id_49>",
|
||||
"<extra_id_50>",
|
||||
"<extra_id_51>",
|
||||
"<extra_id_52>",
|
||||
"<extra_id_53>",
|
||||
"<extra_id_54>",
|
||||
"<extra_id_55>",
|
||||
"<extra_id_56>",
|
||||
"<extra_id_57>",
|
||||
"<extra_id_58>",
|
||||
"<extra_id_59>",
|
||||
"<extra_id_60>",
|
||||
"<extra_id_61>",
|
||||
"<extra_id_62>",
|
||||
"<extra_id_63>",
|
||||
"<extra_id_64>",
|
||||
"<extra_id_65>",
|
||||
"<extra_id_66>",
|
||||
"<extra_id_67>",
|
||||
"<extra_id_68>",
|
||||
"<extra_id_69>",
|
||||
"<extra_id_70>",
|
||||
"<extra_id_71>",
|
||||
"<extra_id_72>",
|
||||
"<extra_id_73>",
|
||||
"<extra_id_74>",
|
||||
"<extra_id_75>",
|
||||
"<extra_id_76>",
|
||||
"<extra_id_77>",
|
||||
"<extra_id_78>",
|
||||
"<extra_id_79>",
|
||||
"<extra_id_80>",
|
||||
"<extra_id_81>",
|
||||
"<extra_id_82>",
|
||||
"<extra_id_83>",
|
||||
"<extra_id_84>",
|
||||
"<extra_id_85>",
|
||||
"<extra_id_86>",
|
||||
"<extra_id_87>",
|
||||
"<extra_id_88>",
|
||||
"<extra_id_89>",
|
||||
"<extra_id_90>",
|
||||
"<extra_id_91>",
|
||||
"<extra_id_92>",
|
||||
"<extra_id_93>",
|
||||
"<extra_id_94>",
|
||||
"<extra_id_95>",
|
||||
"<extra_id_96>",
|
||||
"<extra_id_97>",
|
||||
"<extra_id_98>",
|
||||
"<extra_id_99>"
|
||||
],
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "</s>",
|
||||
"extra_ids": 100,
|
||||
"legacy": false,
|
||||
"model_max_length": 512,
|
||||
"pad_token": "<pad>",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "T5Tokenizer",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
Reference in New Issue
Block a user