Parallia
/

Fairly-Multilingual-ModernBERT-Embed-BE-DE

Sentence Similarity

sentence-transformers

feature-extraction

Generated from Trainer

dataset_size:8066634

loss:MultipleNegativesRankingLoss

Inference Endpoints

Model card Files Files and versions Community

FremyCompany commited on 10 days ago

Commit

0375458

·

verified ·

1 Parent(s): e77d0c0

Provide pad token in the config

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -11,7 +11,7 @@
   "classifier_bias": false,
   "classifier_dropout": 0.0,
   "classifier_pooling": "mean",
-  "cls_token_id": 0,
   "decoder_bias": true,
   "deterministic_flash_attn": false,
   "embedding_dropout": 0.0,
@@ -39,7 +39,7 @@
   "pad_token_id": 2,
   "position_embedding_type": "absolute",
   "reference_compile": false,
-  "sep_token_id": 0,
   "sparse_pred_ignore_index": -100,
   "sparse_prediction": false,
   "tokenizer_class": "LlamaTokenizerFast",

   "classifier_bias": false,
   "classifier_dropout": 0.0,
   "classifier_pooling": "mean",
+  "cls_token_id": 1,
   "decoder_bias": true,
   "deterministic_flash_attn": false,
   "embedding_dropout": 0.0,
   "pad_token_id": 2,
   "position_embedding_type": "absolute",
   "reference_compile": false,
+  "sep_token_id": 1,
   "sparse_pred_ignore_index": -100,
   "sparse_prediction": false,
   "tokenizer_class": "LlamaTokenizerFast",