Muennighoff commited on
Commit
7c14747
1 Parent(s): 51595e9
Files changed (1) hide show
  1. app.py +9 -5
app.py CHANGED
@@ -341,6 +341,7 @@ EXTERNAL_MODELS = [
341
  "text-search-babbage-001",
342
  "text-search-curie-001",
343
  "text-search-davinci-001",
 
344
  "unsup-simcse-bert-base-uncased",
345
  "use-cmlm-multilingual",
346
  "xlm-roberta-base",
@@ -418,6 +419,7 @@ EXTERNAL_MODEL_TO_LINK = {
418
  "text-search-curie-001": "https://beta.openai.com/docs/guides/embeddings/types-of-embedding-models",
419
  "text-search-babbage-001": "https://beta.openai.com/docs/guides/embeddings/types-of-embedding-models",
420
  "text-search-davinci-001": "https://beta.openai.com/docs/guides/embeddings/types-of-embedding-models",
 
421
  "unsup-simcse-bert-base-uncased": "https://huggingface.co/princeton-nlp/unsup-simcse-bert-base-uncased",
422
  "use-cmlm-multilingual": "https://huggingface.co/sentence-transformers/use-cmlm-multilingual",
423
  "xlm-roberta-base": "https://huggingface.co/xlm-roberta-base",
@@ -494,6 +496,7 @@ EXTERNAL_MODEL_TO_DIM = {
494
  "text-search-babbage-001": 2048,
495
  "text-search-curie-001": 4096,
496
  "text-search-davinci-001": 12288,
 
497
  "unsup-simcse-bert-base-uncased": 768,
498
  "use-cmlm-multilingual": 768,
499
  "xlm-roberta-base": 768,
@@ -561,15 +564,16 @@ EXTERNAL_MODEL_TO_SEQLEN = {
561
  "text2vec-large-chinese": 512,
562
  "text-embedding-ada-002": 8191,
563
  "text-similarity-ada-001": 2046,
564
- "text-similarity-babbage-001": 2046,
565
  "text-similarity-curie-001": 2046,
566
- "text-similarity-davinci-001": 2046,
567
  "text-search-ada-doc-001": 2046,
568
  "text-search-ada-query-001": 2046,
569
- "text-search-ada-001": 2046,
570
- "text-search-babbage-001": 2046,
571
  "text-search-curie-001": 2046,
572
- "text-search-davinci-001": 2046,
 
573
  "use-cmlm-multilingual": 512,
574
  "unsup-simcse-bert-base-uncased": 512,
575
  "xlm-roberta-base": 514,
 
341
  "text-search-babbage-001",
342
  "text-search-curie-001",
343
  "text-search-davinci-001",
344
+ "titan-embed-text-v1",
345
  "unsup-simcse-bert-base-uncased",
346
  "use-cmlm-multilingual",
347
  "xlm-roberta-base",
 
419
  "text-search-curie-001": "https://beta.openai.com/docs/guides/embeddings/types-of-embedding-models",
420
  "text-search-babbage-001": "https://beta.openai.com/docs/guides/embeddings/types-of-embedding-models",
421
  "text-search-davinci-001": "https://beta.openai.com/docs/guides/embeddings/types-of-embedding-models",
422
+ "titan-embed-text-v1": "https://docs.aws.amazon.com/bedrock/latest/userguide/embeddings.html",
423
  "unsup-simcse-bert-base-uncased": "https://huggingface.co/princeton-nlp/unsup-simcse-bert-base-uncased",
424
  "use-cmlm-multilingual": "https://huggingface.co/sentence-transformers/use-cmlm-multilingual",
425
  "xlm-roberta-base": "https://huggingface.co/xlm-roberta-base",
 
496
  "text-search-babbage-001": 2048,
497
  "text-search-curie-001": 4096,
498
  "text-search-davinci-001": 12288,
499
+ "titan-embed-text-v1": 1536,
500
  "unsup-simcse-bert-base-uncased": 768,
501
  "use-cmlm-multilingual": 768,
502
  "xlm-roberta-base": 768,
 
564
  "text2vec-large-chinese": 512,
565
  "text-embedding-ada-002": 8191,
566
  "text-similarity-ada-001": 2046,
567
+ "text-similarity-babbage-001": 2046,
568
  "text-similarity-curie-001": 2046,
569
+ "text-similarity-davinci-001": 2046,
570
  "text-search-ada-doc-001": 2046,
571
  "text-search-ada-query-001": 2046,
572
+ "text-search-ada-001": 2046,
573
+ "text-search-babbage-001": 2046,
574
  "text-search-curie-001": 2046,
575
+ "text-search-davinci-001": 2046,
576
+ "titan-embed-text-v1": 8000,
577
  "use-cmlm-multilingual": 512,
578
  "unsup-simcse-bert-base-uncased": 512,
579
  "xlm-roberta-base": 514,