网站的汉化包怎么做,北京建设高端网站,平面设计logo创意图片,加强网站建设前言
在大模型的生成过程中#xff0c;部分原生的大语言模型未经过特殊的对齐训练#xff0c;往往会“胡说八道”的生成一些敏感词语等用户不想生成的词语#xff0c;最简单粗暴的方式就是在大模型生成的文本之后#xff0c;添加敏感词库等规则手段进行敏感词过滤#xf…前言
在大模型的生成过程中部分原生的大语言模型未经过特殊的对齐训练往往会“胡说八道”的生成一些敏感词语等用户不想生成的词语最简单粗暴的方式就是在大模型生成的文本之后添加敏感词库等规则手段进行敏感词过滤但是在生成过程中生成敏感词仍然耗费了时间和算力成本。
本文以chatglm2-6B为例通过自定义LogitsProcessor实践大模型在生成过程中控制一些词语的生成。
LogitsProcessor
从下面代码可以看到LogitsProcessor的作用就是在生成过程中修改score改变模型输出的概率分布的工具。
class LogitsProcessor:Abstract base class for all logit processors that can be applied during generation.add_start_docstrings(LOGITS_PROCESSOR_INPUTS_DOCSTRING)def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor) - torch.FloatTensor:raise NotImplementedError(f{self.__class__} is an abstract class. Only classes inheriting this class can be called.)class LogitsProcessorList(list):This class can be used to create a list of [LogitsProcessor] or [LogitsWarper] to subsequently process ascores input tensor. This class inherits from list and adds a specific *__call__* method to apply each[LogitsProcessor] or [LogitsWarper] to the inputs.def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) - torch.FloatTensor:rArgs:input_ids (torch.LongTensor of shape (batch_size, sequence_length)):Indices of input sequence tokens in the vocabulary. [What are input IDs?](../glossary#input-ids)scores (torch.FloatTensor of shape (batch_size, config.vocab_size)):Prediction scores of a language modeling head. These can be logits for each vocabulary when not usingbeam search or log softmax for each vocabulary token when using beam searchkwargs (Dict[str, Any], *optional*):Additional kwargs that are specific to a logits processor.Return:torch.FloatTensor of shape (batch_size, config.vocab_size):The processed prediction scores.for processor in self:function_args inspect.signature(processor.__call__).parametersif len(function_args) 2:if not all(arg in kwargs for arg in list(function_args.keys())[2:]):raise ValueError(fMake sure that all the required parameters: {list(function_args.keys())} for f{processor.__class__} are passed to the logits processor.)scores processor(input_ids, scores, **kwargs)else:scores processor(input_ids, scores)return scores
自定义LogitsProcessor实践
回到正题如何自定义LogitsProcessor控制大模型生成的过程呢下面直接上实践代码
class new_logits_processor(LogitsProcessor):def __init__(self, forbid_token_id_list: List[int] None):self.forbid_token_id_list forbid_token_id_listdef __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor) - torch.FloatTensor:for id_ in self.forbid_token_id_list:scores[:, id_] -float(inf)return scoresforbid_token_id_list是不让模型生成词语的id映射列表对于这些抑制生成的词语在自定义logits_processor时将其概率推向负无穷大即可。
chatglm2-6B详细实践代码
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, TextStreamer
from transformers.generation.logits_process import LogitsProcessor, LogitsProcessorList
from typing import List
import torchclass new_logits_processor(LogitsProcessor):def __init__(self, forbid_token_id_list: List[int] None):self.forbid_token_id_list forbid_token_id_listdef __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor) - torch.FloatTensor:for id_ in self.forbid_token_id_list:scores[:, id_] -float(inf)return scoresmodel_path THUDM/chatglm2-6b
tokenizer AutoTokenizer.from_pretrained(model_path, trust_remote_codeTrue)
model AutoModelForSeq2SeqLM.from_pretrained(model_path, trust_remote_codeTrue).to(mps)def add_forbid_words():添加需要抑制的词语这里简单添加了数字和几个词语进行对比:return:listforbid_words []for i in range(10):forbid_words.append(tokenizer.convert_tokens_to_ids(str(i)))forbid_words.append(tokenizer.convert_tokens_to_ids(首先))forbid_words.append(tokenizer.convert_tokens_to_ids(积极))forbid_words.append(tokenizer.convert_tokens_to_ids(回答))forbid_words.append(tokenizer.convert_tokens_to_ids(勇敢))forbid_words.append(tokenizer.convert_tokens_to_ids(勇气))return forbid_wordslogits_processor LogitsProcessorList()
logits_processor.append(new_logits_processor(add_forbid_words()))streamer TextStreamer(tokenizer, skip_promptTrue, skip_special_tokensTrue)input 列举出10个积极的词语outputs model.generate(tokenizer(input, return_tensorspt).input_ids.to(mps),max_new_tokens1024,logits_processorlogits_processor, # 不开启注释即可streamerstreamer
)
decode_text tokenizer.batch_decode(outputs, streamerstreamer)[0]
print(decode_text)抑制前输出
1. 勇敢
2. 快乐
3. 成功
4. 努力
5. 积极
6. 乐观
7. 自信
8. 开朗
9. 团结
10. 奋斗抑制后输出
- 积极主动
- 乐观向上
- 自信
- 自律
- 诚实守信
- 乐于助人
- 勇于尝试
- 坚韧不拔
- 乐观开朗
- 团结一心小结
本文通过自定义LogitsProcessor简单的实践了大语言模型在生成过程中屏蔽生成用户自定义词语的trick。在现实场景中根据特定场景探索如何灵活的利用LogitsProcessor进行有针对性的控制生成模型的生成过程非常重要。
参考文献
【1】https://github.com/huggingface/transformers/blob/v4.31.0/src/transformers/generation/logits_process.py
