Muennighoff commited on
Commit
c9eda65
1 Parent(s): ef195e8

Add German models

Browse files
Files changed (1) hide show
  1. app.py +33 -3
app.py CHANGED
@@ -151,6 +151,12 @@ EXTERNAL_MODELS = [
151
  "allenai-specter",
152
  "bert-base-uncased",
153
  "contriever-base-msmarco",
 
 
 
 
 
 
154
  "glove.6B.300d",
155
  "gtr-t5-base",
156
  "gtr-t5-large",
@@ -164,19 +170,33 @@ EXTERNAL_MODELS = [
164
  "sentence-t5-large",
165
  "sentence-t5-xl",
166
  "sentence-t5-xxl",
 
 
167
  "sup-simcse-bert-base-uncased",
168
  "text-embedding-ada-002",
169
  "text-similarity-ada-001",
170
- "text-similarity-babbage-001",
171
- "text-similarity-curie-001",
172
- "text-similarity-davinci-001",
 
173
  "text-search-ada-001",
174
  "text-search-babbage-001",
175
  "text-search-curie-001",
176
  "text-search-davinci-001",
177
  "unsup-simcse-bert-base-uncased",
 
 
178
  ]
 
179
  EXTERNAL_MODEL_TO_LINK = {
 
 
 
 
 
 
 
 
180
  "LASER2": "https://github.com/facebookresearch/LASER",
181
  "text-embedding-ada-002": "https://beta.openai.com/docs/guides/embeddings/types-of-embedding-models",
182
  "text-similarity-ada-001": "https://beta.openai.com/docs/guides/embeddings/types-of-embedding-models",
@@ -218,6 +238,16 @@ EXTERNAL_MODEL_TO_LINK = {
218
  }
219
 
220
  EXTERNAL_MODEL_TO_DIM = {
 
 
 
 
 
 
 
 
 
 
221
  "LASER2": 1024,
222
  "LaBSE": 768,
223
  "all-MiniLM-L12-v2": 384,
 
151
  "allenai-specter",
152
  "bert-base-uncased",
153
  "contriever-base-msmarco",
154
+ "cross-en-de-roberta-sentence-transformer",
155
+ "gbert-base",
156
+ "gbert-large",
157
+ "gelectra-base",
158
+ "gelectra-large",
159
+ "gottbert-base",
160
  "glove.6B.300d",
161
  "gtr-t5-base",
162
  "gtr-t5-large",
 
170
  "sentence-t5-large",
171
  "sentence-t5-xl",
172
  "sentence-t5-xxl",
173
+ "sgpt-bloom-1b7-nli",
174
+ "sgpt-bloom-7b1-msmarco",
175
  "sup-simcse-bert-base-uncased",
176
  "text-embedding-ada-002",
177
  "text-similarity-ada-001",
178
+ "text-similarity-babbage-001",
179
+ "text-similarity-curie-001",
180
+ "text-similarity-davinci-001",
181
+ "text-search-ada-doc-001",
182
  "text-search-ada-001",
183
  "text-search-babbage-001",
184
  "text-search-curie-001",
185
  "text-search-davinci-001",
186
  "unsup-simcse-bert-base-uncased",
187
+ "use-cmlm-multilingual",
188
+ "xlm-roberta-large",
189
  ]
190
+
191
  EXTERNAL_MODEL_TO_LINK = {
192
+ "xlm-roberta-large": "https://huggingface.co/xlm-roberta-large",
193
+ "use-cmlm-multilingual": "https://huggingface.co/sentence-transformers/use-cmlm-multilingual",
194
+ "cross-en-de-roberta-sentence-transformer": "https://huggingface.co/T-Systems-onsite/cross-en-de-roberta-sentence-transformer",
195
+ "gbert-base": "https://huggingface.co/deepset/gbert-base",
196
+ "gbert-large": "https://huggingface.co/deepset/gbert-large",
197
+ "gelectra-base": "https://huggingface.co/deepset/gelectra-base",
198
+ "gelectra-large": "https://huggingface.co/deepset/gelectra-large",
199
+ "gottbert-base": "https://huggingface.co/uklfr/gottbert-base",
200
  "LASER2": "https://github.com/facebookresearch/LASER",
201
  "text-embedding-ada-002": "https://beta.openai.com/docs/guides/embeddings/types-of-embedding-models",
202
  "text-similarity-ada-001": "https://beta.openai.com/docs/guides/embeddings/types-of-embedding-models",
 
238
  }
239
 
240
  EXTERNAL_MODEL_TO_DIM = {
241
+ "xlm-roberta-large": 1024,
242
+ "use-cmlm-multilingual": 768,
243
+ "gottbert-base": 768,
244
+ "cross-en-de-roberta-sentence-transformer": 768,
245
+ "gbert-base": 768,
246
+ "gbert-large": 1024,
247
+ "gelectra-base": 768,
248
+ "gelectra-large": 1024,
249
+ "gottbert-base": 768,
250
+
251
  "LASER2": 1024,
252
  "LaBSE": 768,
253
  "all-MiniLM-L12-v2": 384,