Skip to content

GitLab

"tests/vscode:/vscode.git/clone" did not exist on "c0b4d72095b715c518f54d7111b539667320228e"
Commit 29c2e267 authored by comfyanonymous's avatar comfyanonymous
Browse files

Better tokenizing code for AuraFlow.

parent b6f09cf6
Expand all Show whitespace changes
Inline Side-by-side
Showing with 25 additions and 1175 deletions
comfy/text_encoders/aura_t5.py
View file @ 29c2e267
from comfy import sd1_clip from comfy import sd1_clip
from transformers import LlamaTokenizerFast from .llama_tokenizer import LLAMATokenizer
import comfy.t5 import comfy.t5
import os import os
...@@ -10,8 +10,8 @@ class PT5XlModel(sd1_clip.SDClipModel): ...@@ -10,8 +10,8 @@ class PT5XlModel(sd1_clip.SDClipModel):
class PT5XlTokenizer(sd1_clip.SDTokenizer): class PT5XlTokenizer(sd1_clip.SDTokenizer):
def __init__(self, embedding_directory=None): def __init__(self, embedding_directory=None):
tokenizer_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), "t5_pile_tokenizer") tokenizer_path = os.path.join(os.path.join(os.path.dirname(os.path.realpath(__file__)), "t5_pile_tokenizer"), "tokenizer.model")
super().__init__(tokenizer_path, pad_with_end=False, embedding_size=2048, embedding_key='pile_t5xl', tokenizer_class=LlamaTokenizerFast, has_start_token=False, pad_to_max_length=False, max_length=99999999, min_length=256, pad_token=1) super().__init__(tokenizer_path, pad_with_end=False, embedding_size=2048, embedding_key='pile_t5xl', tokenizer_class=LLAMATokenizer, has_start_token=False, pad_to_max_length=False, max_length=99999999, min_length=256, pad_token=1)
class AuraT5Tokenizer(sd1_clip.SD1Tokenizer): class AuraT5Tokenizer(sd1_clip.SD1Tokenizer):
def __init__(self, embedding_directory=None): def __init__(self, embedding_directory=None):
......
comfy/text_encoders/llama_tokenizer.py 0 → 100644
View file @ 29c2e267
import os
class LLAMATokenizer:
@staticmethod
def from_pretrained(path):
return LLAMATokenizer(path)
def __init__(self, tokenizer_path):
import sentencepiece
self.tokenizer = sentencepiece.SentencePieceProcessor(model_file=tokenizer_path)
self.end = self.tokenizer.eos_id()
def get_vocab(self):
out = {}
for i in range(self.tokenizer.get_piece_size()):
out[self.tokenizer.id_to_piece(i)] = i
return out
def __call__(self, string):
out = self.tokenizer.encode(string)
out += [self.end]
return {"input_ids": out}
comfy/text_encoders/t5_pile_tokenizer/added_tokens.json deleted 100644 → 0
View file @ b6f09cf6
{
"<extra_id_0>": 32099,
"<extra_id_10>": 32089,
"<extra_id_11>": 32088,
"<extra_id_12>": 32087,
"<extra_id_13>": 32086,
"<extra_id_14>": 32085,
"<extra_id_15>": 32084,
"<extra_id_16>": 32083,
"<extra_id_17>": 32082,
"<extra_id_18>": 32081,
"<extra_id_19>": 32080,
"<extra_id_1>": 32098,
"<extra_id_20>": 32079,
"<extra_id_21>": 32078,
"<extra_id_22>": 32077,
"<extra_id_23>": 32076,
"<extra_id_24>": 32075,
"<extra_id_25>": 32074,
"<extra_id_26>": 32073,
"<extra_id_27>": 32072,
"<extra_id_28>": 32071,
"<extra_id_29>": 32070,
"<extra_id_2>": 32097,
"<extra_id_30>": 32069,
"<extra_id_31>": 32068,
"<extra_id_32>": 32067,
"<extra_id_33>": 32066,
"<extra_id_34>": 32065,
"<extra_id_35>": 32064,
"<extra_id_36>": 32063,
"<extra_id_37>": 32062,
"<extra_id_38>": 32061,
"<extra_id_39>": 32060,
"<extra_id_3>": 32096,
"<extra_id_40>": 32059,
"<extra_id_41>": 32058,
"<extra_id_42>": 32057,
"<extra_id_43>": 32056,
"<extra_id_44>": 32055,
"<extra_id_45>": 32054,
"<extra_id_46>": 32053,
"<extra_id_47>": 32052,
"<extra_id_48>": 32051,
"<extra_id_49>": 32050,
"<extra_id_4>": 32095,
"<extra_id_50>": 32049,
"<extra_id_51>": 32048,
"<extra_id_52>": 32047,
"<extra_id_53>": 32046,
"<extra_id_54>": 32045,
"<extra_id_55>": 32044,
"<extra_id_56>": 32043,
"<extra_id_57>": 32042,
"<extra_id_58>": 32041,
"<extra_id_59>": 32040,
"<extra_id_5>": 32094,
"<extra_id_60>": 32039,
"<extra_id_61>": 32038,
"<extra_id_62>": 32037,
"<extra_id_63>": 32036,
"<extra_id_64>": 32035,
"<extra_id_65>": 32034,
"<extra_id_66>": 32033,
"<extra_id_67>": 32032,
"<extra_id_68>": 32031,
"<extra_id_69>": 32030,
"<extra_id_6>": 32093,
"<extra_id_70>": 32029,
"<extra_id_71>": 32028,
"<extra_id_72>": 32027,
"<extra_id_73>": 32026,
"<extra_id_74>": 32025,
"<extra_id_75>": 32024,
"<extra_id_76>": 32023,
"<extra_id_77>": 32022,
"<extra_id_78>": 32021,
"<extra_id_79>": 32020,
"<extra_id_7>": 32092,
"<extra_id_80>": 32019,
"<extra_id_81>": 32018,
"<extra_id_82>": 32017,
"<extra_id_83>": 32016,
"<extra_id_84>": 32015,
"<extra_id_85>": 32014,
"<extra_id_86>": 32013,
"<extra_id_87>": 32012,
"<extra_id_88>": 32011,
"<extra_id_89>": 32010,
"<extra_id_8>": 32091,
"<extra_id_90>": 32009,
"<extra_id_91>": 32008,
"<extra_id_92>": 32007,
"<extra_id_93>": 32006,
"<extra_id_94>": 32005,
"<extra_id_95>": 32004,
"<extra_id_96>": 32003,
"<extra_id_97>": 32002,
"<extra_id_98>": 32001,
"<extra_id_99>": 32000,
"<extra_id_9>": 32090
}
comfy/text_encoders/t5_pile_tokenizer/special_tokens_map.json deleted 100644 → 0
View file @ b6f09cf6
{
"additional_special_tokens": [
"<extra_id_99>",
"<extra_id_98>",
"<extra_id_97>",
"<extra_id_96>",
"<extra_id_95>",
"<extra_id_94>",
"<extra_id_93>",
"<extra_id_92>",
"<extra_id_91>",
"<extra_id_90>",
"<extra_id_89>",
"<extra_id_88>",
"<extra_id_87>",
"<extra_id_86>",
"<extra_id_85>",
"<extra_id_84>",
"<extra_id_83>",
"<extra_id_82>",
"<extra_id_81>",
"<extra_id_80>",
"<extra_id_79>",
"<extra_id_78>",
"<extra_id_77>",
"<extra_id_76>",
"<extra_id_75>",
"<extra_id_74>",
"<extra_id_73>",
"<extra_id_72>",
"<extra_id_71>",
"<extra_id_70>",
"<extra_id_69>",
"<extra_id_68>",
"<extra_id_67>",
"<extra_id_66>",
"<extra_id_65>",
"<extra_id_64>",
"<extra_id_63>",
"<extra_id_62>",
"<extra_id_61>",
"<extra_id_60>",
"<extra_id_59>",
"<extra_id_58>",
"<extra_id_57>",
"<extra_id_56>",
"<extra_id_55>",
"<extra_id_54>",
"<extra_id_53>",
"<extra_id_52>",
"<extra_id_51>",
"<extra_id_50>",
"<extra_id_49>",
"<extra_id_48>",
"<extra_id_47>",
"<extra_id_46>",
"<extra_id_45>",
"<extra_id_44>",
"<extra_id_43>",
"<extra_id_42>",
"<extra_id_41>",
"<extra_id_40>",
"<extra_id_39>",
"<extra_id_38>",
"<extra_id_37>",
"<extra_id_36>",
"<extra_id_35>",
"<extra_id_34>",
"<extra_id_33>",
"<extra_id_32>",
"<extra_id_31>",
"<extra_id_30>",
"<extra_id_29>",
"<extra_id_28>",
"<extra_id_27>",
"<extra_id_26>",
"<extra_id_25>",
"<extra_id_24>",
"<extra_id_23>",
"<extra_id_22>",
"<extra_id_21>",
"<extra_id_20>",
"<extra_id_19>",
"<extra_id_18>",
"<extra_id_17>",
"<extra_id_16>",
"<extra_id_15>",
"<extra_id_14>",
"<extra_id_13>",
"<extra_id_12>",
"<extra_id_11>",
"<extra_id_10>",
"<extra_id_9>",
"<extra_id_8>",
"<extra_id_7>",
"<extra_id_6>",
"<extra_id_5>",
"<extra_id_4>",
"<extra_id_3>",
"<extra_id_2>",
"<extra_id_1>",
"<extra_id_0>"
],
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment