update metadata for gte v1.5 series models

#98
Files changed (1) hide show
  1. app.py +18 -0
app.py CHANGED
@@ -453,6 +453,9 @@ EXTERNAL_MODELS = [
453
  "voyage-lite-02-instruct",
454
  "xlm-roberta-base",
455
  "xlm-roberta-large",
 
 
 
456
  ]
457
 
458
  EXTERNAL_MODEL_TO_LINK = {
@@ -583,6 +586,9 @@ EXTERNAL_MODEL_TO_LINK = {
583
  "voyage-lite-02-instruct": "https://docs.voyageai.com/embeddings/",
584
  "xlm-roberta-base": "https://huggingface.co/xlm-roberta-base",
585
  "xlm-roberta-large": "https://huggingface.co/xlm-roberta-large",
 
 
 
586
  }
587
 
588
  EXTERNAL_MODEL_TO_DIM = {
@@ -712,6 +718,9 @@ EXTERNAL_MODEL_TO_DIM = {
712
  "voyage-lite-02-instruct": 1024,
713
  "xlm-roberta-base": 768,
714
  "xlm-roberta-large": 1024,
 
 
 
715
  }
716
 
717
  EXTERNAL_MODEL_TO_SEQLEN = {
@@ -841,6 +850,9 @@ EXTERNAL_MODEL_TO_SEQLEN = {
841
  "voyage-lite-02-instruct": 4000,
842
  "xlm-roberta-base": 514,
843
  "xlm-roberta-large": 514,
 
 
 
844
  }
845
 
846
  EXTERNAL_MODEL_TO_SIZE = {
@@ -941,6 +953,9 @@ EXTERNAL_MODEL_TO_SIZE = {
941
  "voyage-lite-02-instruct": 1220,
942
  "xlm-roberta-base": 279,
943
  "xlm-roberta-large": 560,
 
 
 
944
  }
945
 
946
  PROPRIETARY_MODELS = {
@@ -1208,6 +1223,9 @@ MODELS_TO_SKIP = {
1208
  "McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse",
1209
  "McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp-unsup-simcse",
1210
  "McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp-unsup-simcse",
 
 
 
1211
  }
1212
 
1213
 
 
453
  "voyage-lite-02-instruct",
454
  "xlm-roberta-base",
455
  "xlm-roberta-large",
456
+ "gte-large-en-v1.5",
457
+ "gte-base-en-v1.5",
458
+ "gte-qwen1.5-7b-instruct",
459
  ]
460
 
461
  EXTERNAL_MODEL_TO_LINK = {
 
586
  "voyage-lite-02-instruct": "https://docs.voyageai.com/embeddings/",
587
  "xlm-roberta-base": "https://huggingface.co/xlm-roberta-base",
588
  "xlm-roberta-large": "https://huggingface.co/xlm-roberta-large",
589
+ "gte-large-en-v1.5": "https://huggingface.co/Alibaba-NLP/gte-large-en-v1.5",
590
+ "gte-base-en-v1.5": "https://huggingface.co/Alibaba-NLP/gte-base-en-v1.5",
591
+ "gte-qwen1.5-7b-instruct": "https://huggingface.co/Alibaba-NLP/gte-Qwen1.5-7B-instruct",
592
  }
593
 
594
  EXTERNAL_MODEL_TO_DIM = {
 
718
  "voyage-lite-02-instruct": 1024,
719
  "xlm-roberta-base": 768,
720
  "xlm-roberta-large": 1024,
721
+ "gte-large-en-v1.5": 768,
722
+ "gte-base-en-v1.5": 1024,
723
+ "gte-qwen1.5-7b-instruct": 4096,
724
  }
725
 
726
  EXTERNAL_MODEL_TO_SEQLEN = {
 
850
  "voyage-lite-02-instruct": 4000,
851
  "xlm-roberta-base": 514,
852
  "xlm-roberta-large": 514,
853
+ "gte-large-en-v1.5": 8192,
854
+ "gte-base-en-v1.5": 8192,
855
+ "gte-qwen1.5-7b-instruct": 32768
856
  }
857
 
858
  EXTERNAL_MODEL_TO_SIZE = {
 
953
  "voyage-lite-02-instruct": 1220,
954
  "xlm-roberta-base": 279,
955
  "xlm-roberta-large": 560,
956
+ "gte-large-en-v1.5": 137,
957
+ "gte-base-en-v1.5": 434,
958
+ "gte-qwen1.5-7b-instruct": 7099
959
  }
960
 
961
  PROPRIETARY_MODELS = {
 
1223
  "McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse",
1224
  "McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp-unsup-simcse",
1225
  "McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp-unsup-simcse",
1226
+ "Alibaba-NLP/gte-Qwen1.5-7B-instruct",
1227
+ "Alibaba-NLP/gte-base-en-v1.5",
1228
+ "Alibaba-NLP/gte-large-en-v1.5",
1229
  }
1230
 
1231