File size: 10,647 Bytes
ce6a2ba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e227e49
ce6a2ba
 
 
 
 
 
 
 
 
 
 
e227e49
ce6a2ba
 
 
 
 
 
 
 
 
 
 
e227e49
ce6a2ba
 
 
 
 
 
 
 
 
 
 
e227e49
ce6a2ba
 
 
 
 
 
 
 
 
 
 
e227e49
ce6a2ba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b65a786
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ce6a2ba
 
 
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
[
            {   "name":"SGPT-125M-Search", 
                "model":"Muennighoff/SGPT-125M-weightedmean-msmarco-specb-bitfit",
                "fork_url":"https://github.com/taskswithcode/sgpt",
                "orig_author_url":"https://github.com/Muennighoff",
                "orig_author":"Niklas Muennighoff",
                "sota_info": {   
                                 "task":"#1 in multiple information retrieval & search tasks(smaller variant)",
                                 "sota_link":"https://paperswithcode.com/paper/sgpt-gpt-sentence-embeddings-for-semantic"
                            },
                "paper_url":"https://arxiv.org/abs/2202.08904v5",
                "mark":"True",
                "class":"SGPTQnAModel"},
            {   "name":"GPT-Neo-125M", 
                "model":"EleutherAI/gpt-neo-125M",
                "fork_url":"https://github.com/taskswithcode/sgpt",
                "orig_author_url":"https://www.eleuther.ai/",
                "orig_author":"EleuthorAI",
                "sota_info": {   
                                 "task":"Top 20 in multiple NLP tasks (smaller variant)",
                                 "sota_link":"https://paperswithcode.com/paper/gpt-neox-20b-an-open-source-autoregressive-1"
                            },
                "paper_url":"https://zenodo.org/record/5551208#.YyV0k-zMLX0",
                "mark":"True",
                "class":"CausalLMModel"},

            {   "name":"sentence-transformers/all-MiniLM-L6-v2", 
                "model":"sentence-transformers/all-MiniLM-L6-v2",
                "fork_url":"https://github.com/taskswithcode/sentence_similarity_hf_model",
                "orig_author_url":"https://github.com/UKPLab",
                "orig_author":"Ubiquitous Knowledge Processing Lab",
                "sota_info": {   
                                 "task":"Over 3.8  million downloads from Huggingface",
                                 "sota_link":"https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2"
                            },
                "paper_url":"https://arxiv.org/abs/1908.10084",
                "mark":"True",
                "class":"HFModel"},
            {   "name":"sentence-transformers/paraphrase-MiniLM-L6-v2", 
                "model":"sentence-transformers/paraphrase-MiniLM-L6-v2",
                "fork_url":"https://github.com/taskswithcode/sentence_similarity_hf_model",
                "orig_author_url":"https://github.com/UKPLab",
                "orig_author":"Ubiquitous Knowledge Processing Lab",
                "sota_info": {   
                                 "task":"Over 2 million downloads from Huggingface",
                                 "sota_link":"https://huggingface.co/sentence-transformers/paraphrase-MiniLM-L6-v2"
                            },
                "paper_url":"https://arxiv.org/abs/1908.10084",
                "mark":"True",
                "class":"HFModel"},
            {   "name":"sentence-transformers/bert-base-nli-mean-tokens", 
                "model":"sentence-transformers/bert-base-nli-mean-tokens",
                "fork_url":"https://github.com/taskswithcode/sentence_similarity_hf_model",
                "orig_author_url":"https://github.com/UKPLab",
                "orig_author":"Ubiquitous Knowledge Processing Lab",
                "sota_info": {   
                                 "task":"Over 700,000 downloads from Huggingface",
                                 "sota_link":"https://huggingface.co/sentence-transformers/bert-base-nli-mean-tokens"
                            },
                "paper_url":"https://arxiv.org/abs/1908.10084",
                "mark":"True",
                "class":"HFModel"},
            {   "name":"sentence-transformers/all-mpnet-base-v2", 
                "model":"sentence-transformers/all-mpnet-base-v2",
                "fork_url":"https://github.com/taskswithcode/sentence_similarity_hf_model",
                "orig_author_url":"https://github.com/UKPLab",
                "orig_author":"Ubiquitous Knowledge Processing Lab",
                "sota_info": {   
                                 "task":"Over 500,000 downloads from Huggingface",
                                 "sota_link":"https://huggingface.co/sentence-transformers/all-mpnet-base-v2"
                            },
                "paper_url":"https://arxiv.org/abs/1908.10084",
                "mark":"True",
                "class":"HFModel"},
            {   "name":"sentence-transformers/all-MiniLM-L12-v2",
                "model":"sentence-transformers/all-MiniLM-L12-v2",
                "fork_url":"https://github.com/taskswithcode/sentence_similarity_hf_model",
                "orig_author_url":"https://github.com/UKPLab",
                "orig_author":"Ubiquitous Knowledge Processing Lab",
                "sota_info": {   
                                 "task":"Over 500,000 downloads from Huggingface",
                                 "sota_link":"https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2"
                            },
                "paper_url":"https://arxiv.org/abs/1908.10084",
                "mark":"True",
                "class":"HFModel"},

            {   "name":"SGPT-125M", 
                "model":"Muennighoff/SGPT-125M-weightedmean-nli-bitfit",
                "fork_url":"https://github.com/taskswithcode/sgpt",
                "orig_author_url":"https://github.com/Muennighoff",
                "orig_author":"Niklas Muennighoff",
                "sota_info": {   
                                 "task":"#1 in multiple information retrieval & search tasks(smaller variant)",
                                 "sota_link":"https://paperswithcode.com/paper/sgpt-gpt-sentence-embeddings-for-semantic"
                            },
                "paper_url":"https://arxiv.org/abs/2202.08904v5",
                "mark":"True",
                "class":"SGPTModel"},
            {  "name":"SIMCSE-base" ,
                "model":"princeton-nlp/sup-simcse-roberta-base",
                "fork_url":"https://github.com/taskswithcode/SimCSE",
                "orig_author_url":"https://github.com/princeton-nlp",
                "orig_author":"Princeton Natural Language Processing",
                "sota_info": {   
                                 "task":"Within top 10 in multiple semantic textual similarity tasks(smaller variant)",
                                 "sota_link":"https://paperswithcode.com/paper/simcse-simple-contrastive-learning-of"
                            },
                "paper_url":"https://arxiv.org/abs/2104.08821v4",
                "mark":"True",
                "class":"SimCSEModel","sota_link":"https://paperswithcode.com/sota/semantic-textual-similarity-on-sick"},
            {  "name":"GPT-3-175B (text-search-davinci-doc-001)" ,
                "model":"text-search-davinci-doc-001",
                "fork_url":"https://openai.com/api/",
                "orig_author_url":"https://openai.com/api/",
                "orig_author":"OpenAI",
                "sota_info": {   
                                 "task":"GPT-3 achieves strong zero-shot and few-shot performance on many NLP datasets etc.",
                                 "sota_link":"https://paperswithcode.com/method/gpt-3"
                            },
                "paper_url":"https://arxiv.org/abs/2005.14165v4",
                "mark":"True",
                "custom_load":"False",
                "Note":"Custom file upload requires OpenAI API access to create embeddings. For API access, use this link ",
                "alt_url":"https://openai.com/api/",
                "class":"OpenAIQnAModel","sota_link":"https://arxiv.org/abs/2005.14165v4"},
            {  "name":"GPT-3-6.7B (text-search-curie-doc-001)" ,
                "model":"text-search-curie-doc-001",
                "fork_url":"https://openai.com/api/",
                "orig_author_url":"https://openai.com/api/",
                "orig_author":"OpenAI",
                "sota_info": {   
                                 "task":"GPT-3 achieves strong zero-shot and few-shot performance on many NLP datasets etc.",
                                 "sota_link":"https://paperswithcode.com/method/gpt-3"
                            },
                "paper_url":"https://arxiv.org/abs/2005.14165v4",
                "mark":"True",
                "custom_load":"False",
                "Note":"Custom file upload requires OpenAI API access to create embeddings. For API access, use this link ",
                "alt_url":"https://openai.com/api/",
                "class":"OpenAIQnAModel","sota_link":"https://arxiv.org/abs/2005.14165v4"},
            {  "name":"GPT-3-1.3B (text-search-babbage-doc-001)" ,
                "model":"text-search-babbage-doc-001",
                "fork_url":"https://openai.com/api/",
                "orig_author_url":"https://openai.com/api/",
                "orig_author":"OpenAI",
                "sota_info": {   
                                 "task":"GPT-3 achieves strong zero-shot and few-shot performance on many NLP datasets etc.",
                                 "sota_link":"https://paperswithcode.com/method/gpt-3"
                            },
                "paper_url":"https://arxiv.org/abs/2005.14165v4",
                "mark":"True",
                "custom_load":"False",
                "Note":"Custom file upload requires OpenAI API access to create embeddings. For API access, use this link ",
                "alt_url":"https://openai.com/api/",
                "class":"OpenAIQnAModel","sota_link":"https://arxiv.org/abs/2005.14165v4"},
            {  "name":"GPT-3-350M (text-search-ada-doc-001)" ,
                "model":"text-search-ada-doc-001",
                "fork_url":"https://openai.com/api/",
                "orig_author_url":"https://openai.com/api/",
                "orig_author":"OpenAI",
                "sota_info": {   
                                 "task":"GPT-3 achieves strong zero-shot and few-shot performance on many NLP datasets etc.",
                                 "sota_link":"https://paperswithcode.com/method/gpt-3"
                            },
                "paper_url":"https://arxiv.org/abs/2005.14165v4",
                "mark":"True",
                "custom_load":"False",
                "Note":"Custom file upload requires OpenAI API access to create embeddings. For API access, use this link ",
                "alt_url":"https://openai.com/api/",
                "class":"OpenAIQnAModel","sota_link":"https://arxiv.org/abs/2005.14165v4"}


            ]