zR
commited on
Commit
•
4f82091
1
Parent(s):
aae8bd7
fix padding
Browse files- tokenization_chatglm.py +4 -103
tokenization_chatglm.py
CHANGED
@@ -1,12 +1,10 @@
|
|
1 |
import regex as re
|
2 |
import base64
|
3 |
import os
|
4 |
-
import json
|
5 |
import tiktoken
|
6 |
-
from
|
7 |
-
from typing import List, Optional, Union, Dict, Any
|
8 |
from transformers import PreTrainedTokenizer
|
9 |
-
from transformers.utils import
|
10 |
from transformers.tokenization_utils_base import EncodedInput, BatchEncoding
|
11 |
|
12 |
|
@@ -17,16 +15,13 @@ class ChatGLM4Tokenizer(PreTrainedTokenizer):
|
|
17 |
def __init__(
|
18 |
self,
|
19 |
vocab_file,
|
20 |
-
padding_side="left",
|
21 |
clean_up_tokenization_spaces=False,
|
22 |
-
encode_special_tokens=False,
|
23 |
**kwargs
|
24 |
):
|
25 |
self.name = "GLM4Tokenizer"
|
26 |
self.vocab_file = vocab_file
|
27 |
pat_str = "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
|
28 |
self.pat_str = re.compile(pat_str)
|
29 |
-
self.encode_special_tokens = encode_special_tokens
|
30 |
|
31 |
mergeable_ranks = {}
|
32 |
with open(vocab_file) as f:
|
@@ -48,7 +43,6 @@ class ChatGLM4Tokenizer(PreTrainedTokenizer):
|
|
48 |
self.n_words = len(self.decoder)
|
49 |
|
50 |
super().__init__(
|
51 |
-
padding_side=padding_side,
|
52 |
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
53 |
**kwargs
|
54 |
)
|
@@ -141,99 +135,6 @@ class ChatGLM4Tokenizer(PreTrainedTokenizer):
|
|
141 |
else:
|
142 |
return str(f"<|{role}|>{metadata}\n{message}")
|
143 |
|
144 |
-
# Use Jinja Template in tokenizer_config.json
|
145 |
-
# def apply_chat_template(
|
146 |
-
# self,
|
147 |
-
# conversation: Union[List[Dict[str, str]], List[List[Dict[str, str]]], "Conversation"],
|
148 |
-
# add_generation_prompt: bool = False,
|
149 |
-
# tokenize: bool = True,
|
150 |
-
# padding: bool = False,
|
151 |
-
# truncation: bool = False,
|
152 |
-
# max_length: Optional[int] = None,
|
153 |
-
# return_tensors: Optional[Union[str, TensorType]] = None,
|
154 |
-
# return_dict: bool = False,
|
155 |
-
# tokenizer_kwargs: Optional[Dict[str, Any]] = None,
|
156 |
-
# add_special_tokens: bool = True,
|
157 |
-
# **kwargs,
|
158 |
-
# ) -> Union[str, List[int], List[str], List[List[int]], BatchEncoding]:
|
159 |
-
#
|
160 |
-
# if return_dict and not tokenize:
|
161 |
-
# raise ValueError(
|
162 |
-
# "`return_dict=True` is incompatible with `tokenize=False`, because there is no dict "
|
163 |
-
# "of tokenizer outputs to return."
|
164 |
-
# )
|
165 |
-
#
|
166 |
-
# def handle_single_conversation(conversation):
|
167 |
-
# input_ids = self.get_prefix_tokens() if add_special_tokens else []
|
168 |
-
# input_message = "[gMASK]<sop>" if add_special_tokens else ""
|
169 |
-
# for item in conversation:
|
170 |
-
# if item.get("tools"):
|
171 |
-
# tools = item["tools"]
|
172 |
-
# content = "你是一个名为 GhatGLM 的人工智能助手。你是基于智谱AI训练的语言模型 GLM-4 模型开发的,你的任务是针对用户的问题和要求提供适当的答复和支持。"
|
173 |
-
# content += "\n\n# 可用工具"
|
174 |
-
# for tool in tools:
|
175 |
-
# if tool["type"] == "function":
|
176 |
-
# function = tool["function"]
|
177 |
-
# content += f"\n\n## {function['name']}\n\n{json.dumps(function, ensure_ascii=False, indent=4)}"
|
178 |
-
# content += "\n在调用上述函数时,请使用 Json 格式表示调用的参数。"
|
179 |
-
# elif tool["type"] == "python":
|
180 |
-
# content += "\n\n## python\n\n当你向 `python` 发送包含 Python 代码的消息时,该代码将会在一个有状态的 Jupyter notebook 环境中执行。\n`python` 返回代码执行的输出,或在执行 60 秒后返回超时。\n`/mnt/data` 将会持久化存储你的文件。在此会话中,`python` 无法访问互联网。不要使用 `python` 进行任何网络请求或者在线 API 调用,这些在线内容的访问将不会成功。"
|
181 |
-
# elif tool["type"] == "simple_browser":
|
182 |
-
# content += "\n\n## simple_browser\n\n你可以使用 `simple_browser` 工具。该工具支持以下函数:\n`search(query: str, recency_days: int)`:使用搜索引擎进行查询并显示结果,可以使用 `recency_days` 参数控制搜索内容的时效性。\n`mclick(ids: list[int])`:获取一系列指定 id 的页面内容。每次调用时,须选择3-10个页面。选择多个角度的页面,同时尽可能选择可信任的信息来源。考虑到部分页面是无法加载的,你也可以多打开一些可能有用的页面而不用担心内容过多。\n`open_url(url: str)`:打开指定的 URL。\n\n使用 `【{引用 id}†{引用文本}】` 来引用内容。\n\n操作步骤:1. 使用 `search` 来获得信息列表; 2. 使用 `mclick` 来获取指定 ID 页面的内容; 3. 根据获得的内容进行回复。在���复中应当引用信息来源。\n 如果用户提供了 URL,也可以用 `open_url` 直接打开页面。\n如果初次搜索结果没有找到合适的信息,也可以再次使用 `search` 进行搜索。"
|
183 |
-
# elif tool["type"] == "cogview":
|
184 |
-
# content += "\n\n## cogview\n\n如果用户的请求中包含了对图像的描述,你可以使用 `cogview` 来生成图像并展示给用户。你需要向 `cogview` 发送图像描述,规则:\n- 发送给 `cogview` 的消息必须使用英语。用户的中文描述必须完全翻译为英语。\n- 应当尽可能详细地描述图像生成的需求,需求描述约 100 英文单词。\n- 保持用户原始描述的意图。不要虚构内容或者没见过的人物。\n- 如无特殊说明,所在地为中国,持有中国立场并遵循中国社会主义价值观。"
|
185 |
-
# else:
|
186 |
-
# raise NotImplementedError(f"Unknown tool type {tool['type']}")
|
187 |
-
# input = self.build_single_message("system", "", content, tokenize=tokenize)
|
188 |
-
# if tokenize:
|
189 |
-
# input_ids.extend(input)
|
190 |
-
# else:
|
191 |
-
# input_message += input
|
192 |
-
# if item["content"]:
|
193 |
-
# input = self.build_single_message(
|
194 |
-
# item["role"],
|
195 |
-
# item.get("metadata", ""),
|
196 |
-
# item["content"],
|
197 |
-
# tokenize=tokenize
|
198 |
-
# )
|
199 |
-
# if tokenize:
|
200 |
-
# input_ids.extend(input)
|
201 |
-
# else:
|
202 |
-
# input_message += input
|
203 |
-
# if add_generation_prompt:
|
204 |
-
# if tokenize:
|
205 |
-
# input_ids.extend([self.convert_tokens_to_ids("<|assistant|>")])
|
206 |
-
# else:
|
207 |
-
# input_message += "<|assistant|>"
|
208 |
-
# return input_ids if tokenize else input_message
|
209 |
-
#
|
210 |
-
# # Main logic to handle different conversation formats
|
211 |
-
# if isinstance(conversation, list) and all(isinstance(i, dict) for i in conversation):
|
212 |
-
# result = handle_single_conversation(conversation)
|
213 |
-
# elif isinstance(conversation, list) and all(isinstance(i, list) for i in conversation):
|
214 |
-
# result = [handle_single_conversation(c) for c in conversation]
|
215 |
-
# elif hasattr(conversation, "messages"):
|
216 |
-
# result = handle_single_conversation(conversation.messages)
|
217 |
-
# else:
|
218 |
-
# raise ValueError("Invalid conversation format")
|
219 |
-
#
|
220 |
-
# if tokenize:
|
221 |
-
# output = self.batch_encode_plus(
|
222 |
-
# [result] if isinstance(result[0], int) else result,
|
223 |
-
# padding=padding,
|
224 |
-
# truncation=truncation,
|
225 |
-
# max_length=max_length,
|
226 |
-
# return_tensors=return_tensors,
|
227 |
-
# is_split_into_words=True,
|
228 |
-
# add_special_tokens=False
|
229 |
-
# )
|
230 |
-
# if return_dict:
|
231 |
-
# return output
|
232 |
-
# else:
|
233 |
-
# return output["input_ids"]
|
234 |
-
# else:
|
235 |
-
# return result
|
236 |
-
|
237 |
def build_inputs_with_special_tokens(
|
238 |
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
|
239 |
) -> List[int]:
|
@@ -263,6 +164,7 @@ class ChatGLM4Tokenizer(PreTrainedTokenizer):
|
|
263 |
self,
|
264 |
encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
|
265 |
max_length: Optional[int] = None,
|
|
|
266 |
padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
|
267 |
pad_to_multiple_of: Optional[int] = None,
|
268 |
return_attention_mask: Optional[bool] = None,
|
@@ -291,7 +193,6 @@ class ChatGLM4Tokenizer(PreTrainedTokenizer):
|
|
291 |
(optional) Set to False to avoid returning attention mask (default: set to model specifics)
|
292 |
"""
|
293 |
# Load from model defaults
|
294 |
-
assert self.padding_side == "left"
|
295 |
|
296 |
required_input = encoded_inputs[self.model_input_names[0]]
|
297 |
seq_length = len(required_input)
|
@@ -320,4 +221,4 @@ class ChatGLM4Tokenizer(PreTrainedTokenizer):
|
|
320 |
encoded_inputs["position_ids"] = [0] * difference + encoded_inputs["position_ids"]
|
321 |
encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
|
322 |
|
323 |
-
return encoded_inputs
|
|
|
1 |
import regex as re
|
2 |
import base64
|
3 |
import os
|
|
|
4 |
import tiktoken
|
5 |
+
from typing import List, Optional, Union, Dict
|
|
|
6 |
from transformers import PreTrainedTokenizer
|
7 |
+
from transformers.utils import PaddingStrategy
|
8 |
from transformers.tokenization_utils_base import EncodedInput, BatchEncoding
|
9 |
|
10 |
|
|
|
15 |
def __init__(
|
16 |
self,
|
17 |
vocab_file,
|
|
|
18 |
clean_up_tokenization_spaces=False,
|
|
|
19 |
**kwargs
|
20 |
):
|
21 |
self.name = "GLM4Tokenizer"
|
22 |
self.vocab_file = vocab_file
|
23 |
pat_str = "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
|
24 |
self.pat_str = re.compile(pat_str)
|
|
|
25 |
|
26 |
mergeable_ranks = {}
|
27 |
with open(vocab_file) as f:
|
|
|
43 |
self.n_words = len(self.decoder)
|
44 |
|
45 |
super().__init__(
|
|
|
46 |
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
47 |
**kwargs
|
48 |
)
|
|
|
135 |
else:
|
136 |
return str(f"<|{role}|>{metadata}\n{message}")
|
137 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
138 |
def build_inputs_with_special_tokens(
|
139 |
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
|
140 |
) -> List[int]:
|
|
|
164 |
self,
|
165 |
encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
|
166 |
max_length: Optional[int] = None,
|
167 |
+
padding_side: str = "left",
|
168 |
padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
|
169 |
pad_to_multiple_of: Optional[int] = None,
|
170 |
return_attention_mask: Optional[bool] = None,
|
|
|
193 |
(optional) Set to False to avoid returning attention mask (default: set to model specifics)
|
194 |
"""
|
195 |
# Load from model defaults
|
|
|
196 |
|
197 |
required_input = encoded_inputs[self.model_input_names[0]]
|
198 |
seq_length = len(required_input)
|
|
|
221 |
encoded_inputs["position_ids"] = [0] * difference + encoded_inputs["position_ids"]
|
222 |
encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
|
223 |
|
224 |
+
return encoded_inputs
|