transformers的所有模型名称和配置的映射记录

方便查看transformers的所有模型

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
("albert", "AlbertConfig"),
("align", "AlignConfig"),
("altclip", "AltCLIPConfig"),
("audio-spectrogram-transformer", "ASTConfig"),
("bart", "BartConfig"),
("beit", "BeitConfig"),
("bert", "BertConfig"),
("bert-generation", "BertGenerationConfig"),
("big_bird", "BigBirdConfig"),
("bigbird_pegasus", "BigBirdPegasusConfig"),
("biogpt", "BioGptConfig"),
("bit", "BitConfig"),
("blenderbot", "BlenderbotConfig"),
("blenderbot-small", "BlenderbotSmallConfig"),
("blip", "BlipConfig"),
("blip-2", "Blip2Config"),
("bloom", "BloomConfig"),
("bridgetower", "BridgeTowerConfig"),
("camembert", "CamembertConfig"),
("canine", "CanineConfig"),
("chinese_clip", "ChineseCLIPConfig"),
("clap", "ClapConfig"),
("clip", "CLIPConfig"),
("clipseg", "CLIPSegConfig"),
("codegen", "CodeGenConfig"),
("conditional_detr", "ConditionalDetrConfig"),
("convbert", "ConvBertConfig"),
("convnext", "ConvNextConfig"),
("convnextv2", "ConvNextV2Config"),
("cpmant", "CpmAntConfig"),
("ctrl", "CTRLConfig"),
("cvt", "CvtConfig"),
("data2vec-audio", "Data2VecAudioConfig"),
("data2vec-text", "Data2VecTextConfig"),
("data2vec-vision", "Data2VecVisionConfig"),
("deberta", "DebertaConfig"),
("deberta-v2", "DebertaV2Config"),
("decision_transformer", "DecisionTransformerConfig"),
("deformable_detr", "DeformableDetrConfig"),
("deit", "DeiTConfig"),
("deta", "DetaConfig"),
("detr", "DetrConfig"),
("dinat", "DinatConfig"),
("distilbert", "DistilBertConfig"),
("donut-swin", "DonutSwinConfig"),
("dpr", "DPRConfig"),
("dpt", "DPTConfig"),
("efficientformer", "EfficientFormerConfig"),
("efficientnet", "EfficientNetConfig"),
("electra", "ElectraConfig"),
("encoder-decoder", "EncoderDecoderConfig"),
("ernie", "ErnieConfig"),
("ernie_m", "ErnieMConfig"),
("esm", "EsmConfig"),
("flaubert", "FlaubertConfig"),
("flava", "FlavaConfig"),
("fnet", "FNetConfig"),
("focalnet", "FocalNetConfig"),
("fsmt", "FSMTConfig"),
("funnel", "FunnelConfig"),
("git", "GitConfig"),
("glpn", "GLPNConfig"),
("gpt-sw3", "GPT2Config"),
("gpt2", "GPT2Config"),
("gpt_bigcode", "GPTBigCodeConfig"),
("gpt_neo", "GPTNeoConfig"),
("gpt_neox", "GPTNeoXConfig"),
("gpt_neox_japanese", "GPTNeoXJapaneseConfig"),
("gptj", "GPTJConfig"),
("gptsan-japanese", "GPTSanJapaneseConfig"),
("graphormer", "GraphormerConfig"),
("groupvit", "GroupViTConfig"),
("hubert", "HubertConfig"),
("ibert", "IBertConfig"),
("imagegpt", "ImageGPTConfig"),
("informer", "InformerConfig"),
("jukebox", "JukeboxConfig"),
("layoutlm", "LayoutLMConfig"),
("layoutlmv2", "LayoutLMv2Config"),
("layoutlmv3", "LayoutLMv3Config"),
("led", "LEDConfig"),
("levit", "LevitConfig"),
("lilt", "LiltConfig"),
("llama", "LlamaConfig"),
("longformer", "LongformerConfig"),
("longt5", "LongT5Config"),
("luke", "LukeConfig"),
("lxmert", "LxmertConfig"),
("m2m_100", "M2M100Config"),
("marian", "MarianConfig"),
("markuplm", "MarkupLMConfig"),
("mask2former", "Mask2FormerConfig"),
("maskformer", "MaskFormerConfig"),
("maskformer-swin", "MaskFormerSwinConfig"),
("mbart", "MBartConfig"),
("mctct", "MCTCTConfig"),
("mega", "MegaConfig"),
("megatron-bert", "MegatronBertConfig"),
("mgp-str", "MgpstrConfig"),
("mobilebert", "MobileBertConfig"),
("mobilenet_v1", "MobileNetV1Config"),
("mobilenet_v2", "MobileNetV2Config"),
("mobilevit", "MobileViTConfig"),
("mpnet", "MPNetConfig"),
("mt5", "MT5Config"),
("mvp", "MvpConfig"),
("nat", "NatConfig"),
("nezha", "NezhaConfig"),
("nllb-moe", "NllbMoeConfig"),
("nystromformer", "NystromformerConfig"),
("oneformer", "OneFormerConfig"),
("open-llama", "OpenLlamaConfig"),
("openai-gpt", "OpenAIGPTConfig"),
("opt", "OPTConfig"),
("owlvit", "OwlViTConfig"),
("pegasus", "PegasusConfig"),
("pegasus_x", "PegasusXConfig"),
("perceiver", "PerceiverConfig"),
("pix2struct", "Pix2StructConfig"),
("plbart", "PLBartConfig"),
("poolformer", "PoolFormerConfig"),
("prophetnet", "ProphetNetConfig"),
("qdqbert", "QDQBertConfig"),
("rag", "RagConfig"),
("realm", "RealmConfig"),
("reformer", "ReformerConfig"),
("regnet", "RegNetConfig"),
("rembert", "RemBertConfig"),
("resnet", "ResNetConfig"),
("retribert", "RetriBertConfig"),
("roberta", "RobertaConfig"),
("roberta-prelayernorm", "RobertaPreLayerNormConfig"),
("roc_bert", "RoCBertConfig"),
("roformer", "RoFormerConfig"),
("rwkv", "RwkvConfig"),
("sam", "SamConfig"),
("segformer", "SegformerConfig"),
("sew", "SEWConfig"),
("sew-d", "SEWDConfig"),
("speech-encoder-decoder", "SpeechEncoderDecoderConfig"),
("speech_to_text", "Speech2TextConfig"),
("speech_to_text_2", "Speech2Text2Config"),
("speecht5", "SpeechT5Config"),
("splinter", "SplinterConfig"),
("squeezebert", "SqueezeBertConfig"),
("swiftformer", "SwiftFormerConfig"),
("swin", "SwinConfig"),
("swin2sr", "Swin2SRConfig"),
("swinv2", "Swinv2Config"),
("switch_transformers", "SwitchTransformersConfig"),
("t5", "T5Config"),
("table-transformer", "TableTransformerConfig"),
("tapas", "TapasConfig"),
("time_series_transformer", "TimeSeriesTransformerConfig"),
("timesformer", "TimesformerConfig"),
("trajectory_transformer", "TrajectoryTransformerConfig"),
("transfo-xl", "TransfoXLConfig"),
("trocr", "TrOCRConfig"),
("tvlt", "TvltConfig"),
("unispeech", "UniSpeechConfig"),
("unispeech-sat", "UniSpeechSatConfig"),
("upernet", "UperNetConfig"),
("van", "VanConfig"),
("videomae", "VideoMAEConfig"),
("vilt", "ViltConfig"),
("vision-encoder-decoder", "VisionEncoderDecoderConfig"),
("vision-text-dual-encoder", "VisionTextDualEncoderConfig"),
("visual_bert", "VisualBertConfig"),
("vit", "ViTConfig"),
("vit_hybrid", "ViTHybridConfig"),
("vit_mae", "ViTMAEConfig"),
("vit_msn", "ViTMSNConfig"),
("wav2vec2", "Wav2Vec2Config"),
("wav2vec2-conformer", "Wav2Vec2ConformerConfig"),
("wavlm", "WavLMConfig"),
("whisper", "WhisperConfig"),
("xclip", "XCLIPConfig"),
("xglm", "XGLMConfig"),
("xlm", "XLMConfig"),
("xlm-prophetnet", "XLMProphetNetConfig"),
("xlm-roberta", "XLMRobertaConfig"),
("xlm-roberta-xl", "XLMRobertaXLConfig"),
("xlnet", "XLNetConfig"),
("xmod", "XmodConfig"),
("yolos", "YolosConfig"),
("yoso", "YosoConfig"),

saleforce的模型下载地址

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP2/blip2_pretrained_vitL.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP/blip_okvqa.pth
https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_large.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP2/blip2_caption_opt6.7b.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP2/blip2_pretrained_flant5xl.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP2/blip2_caption_opt2.7b.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/ALPRO/alpro_msrvtt_retrieval.pt
https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_large_caption.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/ALBEF/albef_vqav2_lavis.pt
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP/blip_aokvqa.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP2/blip2_caption_flant5xl.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP2/blip2_finetune_coco.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/ALBEF/albef_nlvr_lavis.pt
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/ALPRO/alpro_msvd_qa.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/ALPRO/alpro_msrvtt_qa.pth
https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_large_retrieval_coco.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP2/blip2_pretrained_opt2.7b.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/ALBEF/albef_flickr_retrieval_lavis.pt
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP2/blip2_pretrained_opt6.7b.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/ALBEF/albef_snli_ve_lavis.pt
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP2/blip2_pretrained.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/ALBEF/albef_coco_retrieval_lavis.pt
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP2/blip2_pretrained_flant5xl_vitL.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP/blip_coco_caption_base.pth
https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base_retrieval_coco.pth
https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base_vqa_capfilt_large.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP2/blip2_pretrained_flant5xxl.pth
openai
https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base_capfilt_large.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/ALPRO/alpro_pretrain.pt
https://storage.googleapis.com/sfr-pcl-data-research/ALBEF/pretrain_model_nlvr.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/ALPRO/alpro_didemo_retrieval.pt
https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base_caption_capfilt_large.pth
https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base_nlvr.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP/blip_coco_retrieval.pth
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP/blip_flickr_retrieval.pth
https://storage.googleapis.com/sfr-pcl-data-research/ALBEF/ALBEF.pth

具体模型

OPT: Open Pre-trained Transformers (OPT),Meta开发,参数范围从 125M 到 175B,因果模型,文本生成,分类,问答


transformers的所有模型名称和配置的映射记录
https://johnson7788.github.io/2023/05/16/transformers%E7%9A%84%E6%89%80%E6%9C%89%E6%A8%A1%E5%9E%8B%E5%90%8D%E7%A7%B0%E5%92%8C%E9%85%8D%E7%BD%AE%E7%9A%84%E6%98%A0%E5%B0%84%E8%AE%B0%E5%BD%95/
作者
Johnson
发布于
2023年5月16日
许可协议