bert4torch 0.5.4

an elegant bert4torch

Documentation | Torch4keras | Examples | build_MiniLLM_from_scratch | bert4vector

目录

• 目录
• 1. 下载安装
• 2. 功能
• 3. 快速上手
  • 3.1 上手教程
  • 3.2 命令行快速部署大模型服务
• 4. 版本和更新历史
  • 4.1 版本历史
  • 4.2 更新历史
• 5. 预训练权重
• 6. 鸣谢
• 7. 引用
• 8. 其他

1. 下载安装

安装稳定版

pip install bert4torch

安装最新版

pip install git+https://github.com/Tongjilibo/bert4torch

• 注意事项：pip包的发布慢于git上的开发版本，git clone注意引用路径，注意权重是否需要转换
• 测试用例：git clone https://github.com/Tongjilibo/bert4torch，修改example中的预训练模型文件路径和数据路径即可启动脚本
• 自行训练：针对自己的数据，修改相应的数据处理代码块
• 开发环境：原使用torch==1.10版本进行开发，现已切换到torch2.0开发，如其他版本遇到不适配，欢迎反馈

2. 功能

• LLM模型: 加载chatglm、llama、 baichuan、ziya、bloom等开源大模型权重进行推理和微调，命令行一行部署大模型

• 核心功能：加载bert、roberta、albert、xlnet、nezha、bart、RoFormer、RoFormer_V2、ELECTRA、GPT、GPT2、T5、GAU-alpha、ERNIE等预训练权重继续进行finetune、并支持在bert基础上灵活定义自己模型

• 丰富示例：包含llm、pretrain、sentence_classfication、sentence_embedding、sequence_labeling、relation_extraction、seq2seq、serving等多种解决方案

• 实验验证：已在公开数据集实验验证，使用如下examples数据集和实验指标

• 易用trick：集成了常见的trick，即插即用

• 其他特性：加载transformers库模型一起使用；调用方式简洁高效；有训练进度条动态展示；配合torchinfo打印参数量；默认Logger和Tensorboard简便记录训练过程；自定义fit过程，满足高阶需求

• 训练过程：

  

功能	bert4torch	transformers	备注
训练进度条	✅	✅	进度条打印loss和定义的metrics
分布式训练dp/ddp	✅	✅	torch自带dp/ddp
各类callbacks	✅	✅	日志/tensorboard/earlystop/wandb等
大模型推理，stream/batch输出	✅	✅	各个模型是通用的，无需单独维护脚本
大模型微调	✅	✅	lora依赖peft库，pv2自带
丰富tricks	✅	❌	对抗训练等tricks即插即用
代码简洁易懂，自定义空间大	✅	❌	代码复用度高, keras代码训练风格
仓库的维护能力/影响力/使用量/兼容性	❌	✅	目前仓库个人维护
一键部署大模型

3. 快速上手

3.1 上手教程

• Quick-Start
• 快速上手教程，教程示例，实战示例
• bert4torch介绍(知乎)，bert4torch快速上手(知乎)，bert4torch又双叒叕更新啦(知乎)

3.2 命令行快速部署大模型服务

• 本地 / 联网加载

  # 联网下载全部文件
  bert4torch-llm-server --checkpoint_path Qwen2-0.5B-Instruct
  
  # 加载本地大模型，联网下载bert4torch_config.json
  bert4torch-llm-server --checkpoint_path /data/pretrain_ckpt/Qwen/Qwen2-0.5B-Instruct --config_path Qwen/Qwen2-0.5B-Instruct
  
  # 加载本地大模型，且bert4torch_config.json已经下载并放于同名目录下
  bert4torch-llm-server --checkpoint_path /data/pretrain_ckpt/Qwen/Qwen2-0.5B-Instruct
  

• 命令行 / gradio网页 / openai_api

  # 命令行
  bert4torch-llm-server --checkpoint_path /data/pretrain_ckpt/Qwen/Qwen2-0.5B-Instruct --mode cli
  
  # gradio网页
  bert4torch-llm-server --checkpoint_path /data/pretrain_ckpt/Qwen/Qwen2-0.5B-Instruct --mode gradio
  
  # openai_api
  bert4torch-llm-server --checkpoint_path /data/pretrain_ckpt/Qwen/Qwen2-0.5B-Instruct --mode openai
  

• 命令行聊天示例

4. 版本和更新历史

4.1 版本历史

更新日期	bert4torch	torch4keras	版本说明
20240928	0.5.4	0.2.7	【新功能】增加deepseek系列、MiniCPM、MiniCPMV、llama3.2、Qwen2.5；支持device_map=auto;【修复】修复batch_generate和n>1的bug
20240814	0.5.3	0.2.6	【新功能】增加llama3.1/Yi1.5；自动选择从hfmirror下载；支持命令行参数bert4torch-llm-server
20240801	0.5.2	0.2.5	【新功能】chatglm/qwen系列支持function call调用, 增加internlm2系列；【小优化】简化pipeline中chat demo的调用，generate的终止token元素允许为列表, 统一rope_scaling参数名，增加rope衍生类；【bug】修复flash_attn2的推理bug, 修复bart的tie_word_embedding的bug

更多版本

4.2 更新历史

更多历史

5. 预训练权重

• 预训练模型支持多种代码加载方式

  from bert4torch.models import build_transformer_model
  
  # 1. 仅指定config_path: 从头初始化模型结构, 不加载预训练模型
  model = build_transformer_model('./model/bert4torch_config.json')
  
  # 2. 仅指定checkpoint_path: 
  ## 2.1 文件夹路径: 自动寻找路径下的*.bin/*.safetensors权重文件 + 需把bert4torch_config.json下载并放于该目录下
  model = build_transformer_model(checkpoint_path='./model')
  
  ## 2.2 文件路径/列表: 文件路径即权重路径/列表, bert4torch_config.json会从同级目录下寻找
  model = build_transformer_model(checkpoint_path='./pytorch_model.bin')
  
  ## 2.3 model_name: hf上预训练权重名称, 会自动下载hf权重以及bert4torch_config.json文件
  model = build_transformer_model(checkpoint_path='bert-base-chinese')
  
  # 3. 同时指定config_path和checkpoint_path(本地路径名或model_name排列组合): 
  #    本地路径从本地加载，pretrained_model_name会联网下载
  config_path = './model/bert4torch_config.json'  # 或'bert-base-chinese'
  checkpoint_path = './model/pytorch_model.bin'  # 或'bert-base-chinese'
  model = build_transformer_model(config_path, checkpoint_path)
  

• 预训练权重链接和bert4torch_config.json

模型分类	模型名称	权重来源	权重链接/checkpoint_path	config_path
bert	bert-base-chinese	google-bert	bert-base-chinese	bert-base-chinese
	chinese_L-12_H-768_A-12	谷歌	tf权重 Tongjilibo/bert-chinese_L-12_H-768_A-12
	chinese-bert-wwm-ext	HFL	hfl/chinese-bert-wwm-ext	hfl/chinese-bert-wwm-ext
	bert-base-multilingual-cased	google-bert	bert-base-multilingual-cased	bert-base-multilingual-cased
	MacBERT	HFL	hfl/chinese-macbert-base hfl/chinese-macbert-large	hfl/chinese-macbert-base hfl/chinese-macbert-large
	WoBERT	追一科技	junnyu/wobert_chinese_base，junnyu/wobert_chinese_plus_base	junnyu/wobert_chinese_base junnyu/wobert_chinese_plus_base
roberta	chinese-roberta-wwm-ext	HFL	hfl/chinese-roberta-wwm-ext hfl/chinese-roberta-wwm-ext-large (large的mlm权重是随机初始化)	hfl/chinese-roberta-wwm-ext hfl/chinese-roberta-wwm-ext-large
	roberta-small/tiny	追一科技	Tongjilibo/chinese_roberta_L-4_H-312_A-12 Tongjilibo/chinese_roberta_L-6_H-384_A-12
	roberta-base	FacebookAI	roberta-base	roberta-base
	guwenbert	ethanyt	ethanyt/guwenbert-base	ethanyt/guwenbert-base
albert	albert_zh albert_pytorch	brightmart	voidful/albert_chinese_tiny voidful/albert_chinese_small voidful/albert_chinese_base voidful/albert_chinese_large voidful/albert_chinese_xlarge voidful/albert_chinese_xxlarge	voidful/albert_chinese_tiny，voidful/albert_chinese_small voidful/albert_chinese_base voidful/albert_chinese_large voidful/albert_chinese_xlarge voidful/albert_chinese_xxlarge
nezha	NEZHA NeZha_Chinese_PyTorch	huawei_noah	sijunhe/nezha-cn-base sijunhe/nezha-cn-large sijunhe/nezha-base-wwm sijunhe/nezha-large-wwm	sijunhe/nezha-cn-base sijunhe/nezha-cn-large sijunhe/nezha-base-wwm sijunhe/nezha-large-wwm
	nezha_gpt_dialog	bojone	Tongjilibo/nezha_gpt_dialog
xlnet	Chinese-XLNet	HFL	hfl/chinese-xlnet-base	hfl/chinese-xlnet-base
	tranformer_xl	huggingface	transfo-xl/transfo-xl-wt103	transfo-xl/transfo-xl-wt103
deberta	Erlangshen-DeBERTa-v2	IDEA	IDEA-CCNL/Erlangshen-DeBERTa-v2-97M-Chinese IDEA-CCNL/Erlangshen-DeBERTa-v2-320M-Chinese IDEA-CCNL/Erlangshen-DeBERTa-v2-710M-Chinese	IDEA-CCNL/Erlangshen-DeBERTa-v2-97M-Chinese IDEA-CCNL/Erlangshen-DeBERTa-v2-320M-Chinese IDEA-CCNL/Erlangshen-DeBERTa-v2-710M-Chinese
electra	Chinese-ELECTRA	HFL	hfl/chinese-electra-base-discriminator	hfl/chinese-electra-base-discriminator
ernie	ernie	百度文心	nghuyong/ernie-1.0-base-zh nghuyong/ernie-3.0-base-zh	nghuyong/ernie-1.0-base-zh nghuyong/ernie-3.0-base-zh
roformer	roformer	追一科技	junnyu/roformer_chinese_base	junnyu/roformer_chinese_base
	roformer_v2	追一科技	junnyu/roformer_v2_chinese_char_base	junnyu/roformer_v2_chinese_char_base
simbert	simbert	追一科技	Tongjilibo/simbert-chinese-base Tongjilibo/simbert-chinese-small Tongjilibo/simbert-chinese-tiny
	simbert_v2/roformer-sim	追一科技	junnyu/roformer_chinese_sim_char_base，junnyu/roformer_chinese_sim_char_ft_base，junnyu/roformer_chinese_sim_char_small，junnyu/roformer_chinese_sim_char_ft_small	junnyu/roformer_chinese_sim_char_base junnyu/roformer_chinese_sim_char_ft_base junnyu/roformer_chinese_sim_char_small junnyu/roformer_chinese_sim_char_ft_small
gau	GAU-alpha	追一科技	Tongjilibo/chinese_GAU-alpha-char_L-24_H-768
uie	uie uie_pytorch	百度	Tongjilibo/uie-base
gpt	CDial-GPT	thu-coai	thu-coai/CDial-GPT_LCCC-base thu-coai/CDial-GPT_LCCC-large	thu-coai/CDial-GPT_LCCC-base thu-coai/CDial-GPT_LCCC-large
	cmp_lm(26亿)	清华	TsinghuaAI/CPM-Generate	TsinghuaAI/CPM-Generate
	nezha_gen	huawei_noah	Tongjilibo/chinese_nezha_gpt_L-12_H-768_A-12
	gpt2-chinese-cluecorpussmall	UER	uer/gpt2-chinese-cluecorpussmall	uer/gpt2-chinese-cluecorpussmall
	gpt2-ml	imcaspar	torch BaiduYun(84dh)	gpt2-ml_15g_corpus gpt2-ml_30g_corpus
bart	bart_base_chinese	复旦fnlp	fnlp/bart-base-chinese v1.0	fnlp/bart-base-chinese fnlp/bart-base-chinese-v1.0
t5	t5	UER	uer/t5-small-chinese-cluecorpussmall uer/t5-base-chinese-cluecorpussmall	uer/t5-base-chinese-cluecorpussmall uer/t5-small-chinese-cluecorpussmall
	mt5	谷歌	google/mt5-base	google/mt5-base
	t5_pegasus	追一科技	Tongjilibo/chinese_t5_pegasus_small Tongjilibo/chinese_t5_pegasus_base
	chatyuan	clue-ai	ClueAI/ChatYuan-large-v1 ClueAI/ChatYuan-large-v2	ClueAI/ChatYuan-large-v1 ClueAI/ChatYuan-large-v2
	PromptCLUE	clue-ai	ClueAI/PromptCLUE-base	ClueAI/PromptCLUE-base
chatglm	chatglm-6b	THUDM	THUDM/chatglm-6b THUDM/chatglm-6b-int8 THUDM/chatglm-6b-int4 v0.1.0	THUDM/chatglm-6b THUDM/chatglm-6b-int8 THUDM/chatglm-6b-int4 THUDM/chatglm-6b-v0.1.0
	chatglm2-6b	THUDM	THUDM/chatglm2-6b THUDM/chatglm2-6b-int4 THUDM/chatglm2-6b-32k	THUDM/chatglm2-6b THUDM/chatglm2-6b-int4 THUDM/chatglm2-6b-32k
	chatglm3-6b	THUDM	THUDM/chatglm3-6b THUDM/chatglm3-6b-32k	THUDM/chatglm3-6b THUDM/chatglm3-6b-32k
	glm4-9b	THUDM	THUDM/glm-4-9b THUDM/glm-4-9b-chat THUDM/glm-4-9b-chat-1m	THUDM/glm-4-9b THUDM/glm-4-9b-chat THUDM/glm-4-9b-chat-1m
llama	llama	meta		llama-7b llama-13b
	llama-2	meta	meta-llama/Llama-2-7b-hf meta-llama/Llama-2-7b-chat-hf meta-llama/Llama-2-13b-hf meta-llama/Llama-2-13b-chat-hf	meta-llama/Llama-2-7b-hf meta-llama/Llama-2-7b-chat-hf meta-llama/Llama-2-13b-hf meta-llama/Llama-2-13b-chat-hf
	llama-3	meta	meta-llama/Meta-Llama-3-8B meta-llama/Meta-Llama-3-8B-Instruct	meta-llama/Meta-Llama-3-8B meta-llama/Meta-Llama-3-8B-Instruct
	llama-3.1	meta	meta-llama/Meta-Llama-3.1-8B meta-llama/Meta-Llama-3.1-8B-Instruct	meta-llama/Meta-Llama-3.1-8B meta-llama/Meta-Llama-3.1-8B-Instruct
	llama-3.2	meta	meta-llama/Llama-3.2-1B meta-llama/Llama-3.2-1B-Instruct meta-llama/Llama-3.2-3B meta-llama/Llama-3.2-3B-Instruct	meta-llama/Llama-3.2-1B meta-llama/Llama-3.2-1B-Instruct meta-llama/Llama-3.2-3B meta-llama/Llama-3.2-3B-Instruct
	Chinese-LLaMA-Alpaca	HFL		chinese_alpaca_plus_7b chinese_llama_plus_7b
	Chinese-LLaMA-Alpaca-2	HFL		待添加
	Chinese-LLaMA-Alpaca-3	HFL		待添加
	Belle_llama	LianjiaTech	BelleGroup/BELLE-LLaMA-7B-2M-enc	合成说明、BELLE-LLaMA-7B-2M-enc
	Ziya	IDEA-CCNL	IDEA-CCNL/Ziya-LLaMA-13B-v1 IDEA-CCNL/Ziya-LLaMA-13B-v1.1 IDEA-CCNL/Ziya-LLaMA-13B-Pretrain-v1	IDEA-CCNL/Ziya-LLaMA-13B-v1 IDEA-CCNL/Ziya-LLaMA-13B-v1.1
	vicuna	lmsys	lmsys/vicuna-7b-v1.5	lmsys/vicuna-7b-v1.5
Baichuan	Baichuan	baichuan-inc	baichuan-inc/Baichuan-7B baichuan-inc/Baichuan-13B-Base baichuan-inc/Baichuan-13B-Chat	baichuan-inc/Baichuan-7B baichuan-inc/Baichuan-13B-Base baichuan-inc/Baichuan-13B-Chat
	Baichuan2	baichuan-inc	baichuan-inc/Baichuan2-7B-Base baichuan-inc/Baichuan2-7B-Chat baichuan-inc/Baichuan2-13B-Base baichuan-inc/Baichuan2-13B-Chat	baichuan-inc/Baichuan2-7B-Base baichuan-inc/Baichuan2-7B-Chat baichuan-inc/Baichuan2-13B-Base baichuan-inc/Baichuan2-13B-Chat
Yi	Yi	01-ai	01-ai/Yi-6B 01-ai/Yi-6B-200K 01-ai/Yi-9B 01-ai/Yi-9B-200K	01-ai/Yi-6B 01-ai/Yi-6B-200K 01-ai/Yi-9B 01-ai/Yi-9B-200K
	Yi-1.5	01-ai	01-ai/Yi-1.5-6B 01-ai/Yi-1.5-6B-Chat 01-ai/Yi-1.5-9B 01-ai/Yi-1.5-9B-32K 01-ai/Yi-1.5-9B-Chat 01-ai/Yi-1.5-9B-Chat-16K	01-ai/Yi-1.5-6B 01-ai/Yi-1.5-6B-Chat 01-ai/Yi-1.5-9B 01-ai/Yi-1.5-9B-32K 01-ai/Yi-1.5-9B-Chat 01-ai/Yi-1.5-9B-Chat-16K
bloom	bloom	bigscience	bigscience/bloom-560m bigscience/bloomz-560m	bigscience/bloom-560m bigscience/bloomz-560m
Qwen	Qwen	阿里云	Qwen/Qwen-1_8B Qwen/Qwen-1_8B-Chat Qwen/Qwen-7B Qwen/Qwen-7B-Chat Qwen/Qwen-14B Qwen/Qwen-14B-Chat	Qwen/Qwen-1_8B Qwen/Qwen-1_8B-Chat Qwen/Qwen-7B Qwen/Qwen-7B-Chat Qwen/Qwen-14B Qwen/Qwen-14B-Chat
	Qwen1.5	阿里云	Qwen/Qwen1.5-0.5B Qwen/Qwen1.5-0.5B-Chat Qwen/Qwen1.5-1.8B Qwen/Qwen1.5-1.8B-Chat Qwen/Qwen1.5-7B Qwen/Qwen1.5-7B-Chat Qwen/Qwen1.5-14B Qwen/Qwen1.5-14B-Chat	Qwen/Qwen1.5-0.5B Qwen/Qwen1.5-0.5B-Chat Qwen/Qwen1.5-1.8B Qwen/Qwen1.5-1.8B-Chat Qwen/Qwen1.5-7B Qwen/Qwen1.5-7B-Chat Qwen/Qwen1.5-14B Qwen/Qwen1.5-14B-Chat
	Qwen2	阿里云	Qwen/Qwen2-0.5B Qwen/Qwen2-0.5B-Instruct Qwen/Qwen2-1.5B Qwen/Qwen2-1.5B-Instruct Qwen/Qwen2-7B Qwen/Qwen2-7B-Instruct	Qwen/Qwen2-0.5B Qwen/Qwen2-0.5B-Instruct Qwen/Qwen2-1.5B Qwen/Qwen2-1.5B-Instruct Qwen/Qwen2-7B Qwen/Qwen2-7B-Instruct
	Qwen2.5	阿里云	Qwen/Qwen2.5-0.5B Qwen/Qwen2.5-0.5B-Instruct Qwen/Qwen2.5-1.5B Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-3B Qwen/Qwen2.5-3B-Instruct Qwen/Qwen2.5-7B Qwen/Qwen2.5-7B-Instruct Qwen/Qwen2.5-14B Qwen/Qwen2.5-14B-Instruct	Qwen/Qwen2.5-0.5B Qwen/Qwen2.5-0.5B-Instruct Qwen/Qwen2.5-1.5B Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-3B Qwen/Qwen2.5-3B-Instruct Qwen/Qwen2.5-7B Qwen/Qwen2.5-7B-Instruct Qwen/Qwen2.5-14B Qwen/Qwen2.5-14B-Instruct
InternLM	InternLM	上海人工智能实验室	internlm/internlm-7b internlm/internlm-chat-7b	internlm/internlm-7b internlm/internlm-chat-7b
	InternLM2	上海人工智能实验室	internlm/internlm2-1_8b internlm/internlm2-chat-1_8b internlm/internlm2-7b internlm/internlm2-chat-7b internlm/internlm2-20b internlm/internlm2-chat-20b	internlm/internlm2-1_8b internlm/internlm2-chat-1_8b internlm/internlm2-7b internlm/internlm2-chat-7b
	InternLM2.5	上海人工智能实验室	internlm/internlm2_5-7b internlm/internlm2_5-7b-chat internlm/internlm2_5-7b-chat-1m	internlm/internlm2_5-7b internlm/internlm2_5-7b-chat internlm/internlm2_5-7b-chat-1m
Falcon	Falcon	tiiuae	tiiuae/falcon-rw-1b tiiuae/falcon-7b tiiuae/falcon-7b-instruct	tiiuae/falcon-rw-1b tiiuae/falcon-7b tiiuae/falcon-7b-instruct
DeepSeek	DeepSeek-MoE	深度求索	deepseek-ai/deepseek-moe-16b-base deepseek-ai/deepseek-moe-16b-chat	deepseek-ai/deepseek-moe-16b-base deepseek-ai/deepseek-moe-16b-chat
	DeepSeek-LLM	深度求索	deepseek-ai/deepseek-llm-7b-base deepseek-ai/deepseek-llm-7b-chat	deepseek-ai/deepseek-llm-7b-base deepseek-ai/deepseek-llm-7b-chat
	DeepSeek-V2	深度求索	deepseek-ai/DeepSeek-V2-Lite deepseek-ai/DeepSeek-V2-Lite-Chat	deepseek-ai/DeepSeek-V2-Lite deepseek-ai/DeepSeek-V2-Lite-Chat
	DeepSeek-Coder	深度求索	deepseek-ai/deepseek-coder-1.3b-base deepseek-ai/deepseek-coder-1.3b-instruct deepseek-ai/deepseek-coder-6.7b-base deepseek-ai/deepseek-coder-6.7b-instruct deepseek-ai/deepseek-coder-7b-base-v1.5 deepseek-ai/deepseek-coder-7b-instruct-v1.5	deepseek-ai/deepseek-coder-1.3b-base deepseek-ai/deepseek-coder-1.3b-instruct deepseek-ai/deepseek-coder-6.7b-base deepseek-ai/deepseek-coder-6.7b-instruct deepseek-ai/deepseek-coder-7b-base-v1.5 deepseek-ai/deepseek-coder-7b-instruct-v1.5
	DeepSeek-Coder-V2	深度求索	deepseek-ai/DeepSeek-Coder-V2-Lite-Base deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct	deepseek-ai/DeepSeek-Coder-V2-Lite-Base deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
	DeepSeek-Math	深度求索	deepseek-ai/deepseek-math-7b-base deepseek-ai/deepseek-math-7b-instruct deepseek-ai/deepseek-math-7b-rl	deepseek-ai/deepseek-math-7b-base deepseek-ai/deepseek-math-7b-instruct deepseek-ai/deepseek-math-7b-rl
MiniCPM	MiniCPM	OpenBMB	openbmb/MiniCPM-2B-sft-bf16 openbmb/MiniCPM-2B-dpo-bf16 openbmb/MiniCPM-2B-128k openbmb/MiniCPM-1B-sft-bf16	openbmb/MiniCPM-2B-sft-bf16 openbmb/MiniCPM-2B-dpo-bf16 openbmb/MiniCPM-2B-128k openbmb/MiniCPM-1B-sft-bf16
	MiniCPM-V	OpenBMB	openbmb/MiniCPM-V-2_6 openbmb/MiniCPM-Llama3-V-2_5	openbmb/MiniCPM-V-2_6 openbmb/MiniCPM-Llama3-V-2_5
embedding	text2vec-base-chinese	shibing624	shibing624/text2vec-base-chinese	shibing624/text2vec-base-chinese
	m3e	moka-ai	moka-ai/m3e-base	moka-ai/m3e-base
	bge	BAAI	BAAI/bge-large-en-v1.5 BAAI/bge-large-zh-v1.5 BAAI/bge-base-en-v1.5 BAAI/bge-base-zh-v1.5 BAAI/bge-small-en-v1.5 BAAI/bge-small-zh-v1.5	bge-large-en-v1.5 bge-large-zh-v1.5 bge-base-en-v1.5 bge-base-zh-v1.5 bge-small-en-v1.5 bge-small-zh-v1.5
	gte	thenlper	thenlper/gte-large-zh thenlper/gte-base-zh	thenlper/gte-base-zh thenlper/gte-large-zh

*注：

1. 高亮格式(如bert-base-chinese)的表示可直接build_transformer_model()联网下载
2. 国内镜像网站加速下载
   • HF_ENDPOINT=https://hf-mirror.com python your_script.py
   • export HF_ENDPOINT=https://hf-mirror.com后再执行python代码
   • 在python代码开头如下设置

   import os
   os.environ['HF_ENDPOINT'] = "https://hf-mirror.com"
   

6. 鸣谢

• 感谢苏神实现的bert4keras，本实现有不少地方参考了bert4keras的源码，在此衷心感谢大佬的无私奉献;
• 其次感谢项目bert4pytorch，也是在该项目的指引下给了我用pytorch来复现bert4keras的想法和思路。

7. 引用

@misc{bert4torch,
  title={bert4torch},
  author={Bo Li},
  year={2022},
  howpublished={\url{https://github.com/Tongjilibo/bert4torch}},
}

8. 其他

• Wechat & Star History Chart
• 微信群人数超过200个（有邀请限制），可添加个人微信拉群

微信号

微信群

Star History Chart