Move globals around slightly

app.py

@@ -946,6 +946,104 @@ PROPRIETARY_MODELS = {
     for model in PROPRIETARY_MODELS
 }
 
+SENTENCE_TRANSFORMERS_COMPATIBLE_MODELS = {
+    "allenai-specter",
+    "allenai-specter",
+    "all-MiniLM-L12-v2",
+    "all-MiniLM-L6-v2",
+    "all-mpnet-base-v2",
+    "bert-base-10lang-cased",
+    "bert-base-15lang-cased",
+    "bert-base-25lang-cased",
+    "bert-base-multilingual-cased",
+    "bert-base-multilingual-uncased",
+    "bert-base-swedish-cased",
+    "bert-base-uncased",
+    "bge-base-zh-v1.5",
+    "bge-large-zh-v1.5",
+    "bge-large-zh-noinstruct",
+    "bge-small-zh-v1.5",
+    "camembert-base",
+    "camembert-large",
+    "contriever-base-msmarco",
+    "cross-en-de-roberta-sentence-transformer",
+    "DanskBERT",
+    "distilbert-base-25lang-cased",
+    "distilbert-base-en-fr-cased",
+    "distilbert-base-en-fr-es-pt-it-cased",
+    "distilbert-base-fr-cased",
+    "distilbert-base-uncased",
+    "distiluse-base-multilingual-cased-v2",
+    "dfm-encoder-large-v1",
+    "dfm-sentence-encoder-large-1",
+    "e5-base",
+    "e5-large",
+    "e5-mistral-7b-instruct",
+    "e5-small",
+    "electra-small-nordic",
+    "electra-small-swedish-cased-discriminator",
+    "flaubert_base_cased",
+    "flaubert_base_uncased",
+    "flaubert_large_cased",
+    "gbert-base",
+    "gbert-large",
+    "gelectra-base",
+    "gelectra-large",
+    "glove.6B.300d",
+    "gottbert-base",
+    "gtr-t5-base",
+    "gtr-t5-large",
+    "gtr-t5-xl",
+    "gtr-t5-xxl",
+    "herbert-base-retrieval-v2",
+    "komninos",
+    "luotuo-bert-medium",
+    "LaBSE",
+    "m3e-base",
+    "m3e-large",
+    "msmarco-bert-co-condensor",
+    "multi-qa-MiniLM-L6-cos-v1",
+    "multilingual-e5-base",
+    "multilingual-e5-large",
+    "multilingual-e5-small",
+    "nb-bert-base",
+    "nb-bert-large",
+    "nomic-embed-text-v1.5-64",
+    "nomic-embed-text-v1.5-128",
+    "nomic-embed-text-v1.5-256",
+    "nomic-embed-text-v1.5-512",
+    "norbert3-base",
+    "norbert3-large",
+    "paraphrase-multilingual-mpnet-base-v2",    
+    "paraphrase-multilingual-MiniLM-L12-v2",
+    "sentence-camembert-base",
+    "sentence-camembert-large",
+    "sentence-croissant-llm-base",
+    "sentence-bert-swedish-cased",
+    "sentence-t5-base",
+    "sentence-t5-large",
+    "sentence-t5-xl",
+    "sentence-t5-xxl",
+    "silver-retriever-base-v1",
+    "sup-simcse-bert-base-uncased",
+    "st-polish-paraphrase-from-distilroberta",
+    "st-polish-paraphrase-from-mpnet",
+    "text2vec-base-chinese",
+    "text2vec-large-chinese",
+    "udever-bloom-1b1",
+    "udever-bloom-560m",
+    "universal-sentence-encoder-multilingual-3",
+    "universal-sentence-encoder-multilingual-large-3",
+    "unsup-simcse-bert-base-uncased",
+    "use-cmlm-multilingual",
+    "xlm-roberta-base",
+    "xlm-roberta-large",
+}
+SENTENCE_TRANSFORMERS_COMPATIBLE_MODELS = {
+    make_clickable_model(model, link=EXTERNAL_MODEL_TO_LINK.get(model, "https://huggingface.co/spaces/mteb/leaderboard"))
+    for model in SENTENCE_TRANSFORMERS_COMPATIBLE_MODELS
+}
+
 MODELS_TO_SKIP = {
     "baseplate/instructor-large-1", # Duplicate
     "radames/e5-large", # Duplicate
@@ -1070,103 +1168,6 @@ MODELS_TO_SKIP = {
     "Koat/gte-tiny",
 }
 
-SENTENCE_TRANSFORMERS_COMPATIBLE_MODELS = {
-    "allenai-specter",
-    "allenai-specter",
-    "all-MiniLM-L12-v2",
-    "all-MiniLM-L6-v2",
-    "all-mpnet-base-v2",
-    "bert-base-10lang-cased",
-    "bert-base-15lang-cased",
-    "bert-base-25lang-cased",
-    "bert-base-multilingual-cased",
-    "bert-base-multilingual-uncased",
-    "bert-base-swedish-cased",
-    "bert-base-uncased",
-    "bge-base-zh-v1.5",
-    "bge-large-zh-v1.5",
-    "bge-large-zh-noinstruct",
-    "bge-small-zh-v1.5",
-    "camembert-base",
-    "camembert-large",
-    "contriever-base-msmarco",
-    "cross-en-de-roberta-sentence-transformer",
-    "DanskBERT",
-    "distilbert-base-25lang-cased",
-    "distilbert-base-en-fr-cased",
-    "distilbert-base-en-fr-es-pt-it-cased",
-    "distilbert-base-fr-cased",
-    "distilbert-base-uncased",
-    "distiluse-base-multilingual-cased-v2",
-    "dfm-encoder-large-v1",
-    "dfm-sentence-encoder-large-1",
-    "e5-base",
-    "e5-large",
-    "e5-mistral-7b-instruct",
-    "e5-small",
-    "electra-small-nordic",
-    "electra-small-swedish-cased-discriminator",
-    "flaubert_base_cased",
-    "flaubert_base_uncased",
-    "flaubert_large_cased",
-    "gbert-base",
-    "gbert-large",
-    "gelectra-base",
-    "gelectra-large",
-    "glove.6B.300d",
-    "gottbert-base",
-    "gtr-t5-base",
-    "gtr-t5-large",
-    "gtr-t5-xl",
-    "gtr-t5-xxl",
-    "herbert-base-retrieval-v2",
-    "komninos",
-    "luotuo-bert-medium",
-    "LaBSE",
-    "m3e-base",
-    "m3e-large",
-    "msmarco-bert-co-condensor",
-    "multi-qa-MiniLM-L6-cos-v1",
-    "multilingual-e5-base",
-    "multilingual-e5-large",
-    "multilingual-e5-small",
-    "nb-bert-base",
-    "nb-bert-large",
-    "nomic-embed-text-v1.5-64",
-    "nomic-embed-text-v1.5-128",
-    "nomic-embed-text-v1.5-256",
-    "nomic-embed-text-v1.5-512",
-    "norbert3-base",
-    "norbert3-large",
-    "paraphrase-multilingual-mpnet-base-v2",    
-    "paraphrase-multilingual-MiniLM-L12-v2",
-    "sentence-camembert-base",
-    "sentence-camembert-large",
-    "sentence-croissant-llm-base",
-    "sentence-bert-swedish-cased",
-    "sentence-t5-base",
-    "sentence-t5-large",
-    "sentence-t5-xl",
-    "sentence-t5-xxl",
-    "silver-retriever-base-v1",
-    "sup-simcse-bert-base-uncased",
-    "st-polish-paraphrase-from-distilroberta",
-    "st-polish-paraphrase-from-mpnet",
-    "text2vec-base-chinese",
-    "text2vec-large-chinese",
-    "udever-bloom-1b1",
-    "udever-bloom-560m",
-    "universal-sentence-encoder-multilingual-3",
-    "universal-sentence-encoder-multilingual-large-3",
-    "unsup-simcse-bert-base-uncased",
-    "use-cmlm-multilingual",
-    "xlm-roberta-base",
-    "xlm-roberta-large",
-}
-SENTENCE_TRANSFORMERS_COMPATIBLE_MODELS = {
-    make_clickable_model(model, link=EXTERNAL_MODEL_TO_LINK.get(model, "https://huggingface.co/spaces/mteb/leaderboard"))
-    for model in SENTENCE_TRANSFORMERS_COMPATIBLE_MODELS
-}
 
 def add_lang(examples):
     if not(examples["eval_language"]):