dragonkue
/

multilingual-e5-small-ko

Sentence Similarity

sentence-transformers

feature-extraction

Generated from Trainer

text-embeddings-inference

Model card Files Files and versions

dragonkue commited on May 11, 2025

Commit

fffbfb9

·

verified ·

1 Parent(s): 9375ef3

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -207,7 +207,7 @@ Following the training approach used in dragonkue/snowflake-arctic-embed-l-v2.0-
 This margin-based approach extends the idea proposed in the NV-Retriever paper, which originally filtered false negatives during hard negative sampling.
 We adapt this to in-batch negatives, treating false negatives as dynamic samples guided by margin-based filtering.
-<img src="https://cdn-uploads.huggingface.co/production/uploads/642b0c2fecec03b4464a1d9b/KrtD8Mdmz-ziozXCVz9Zr.png" width="800"/>
 The sentence-transformers library now supports GISTEmbedLoss with margin configuration, making it easy to integrate into any training pipeline.

 This margin-based approach extends the idea proposed in the NV-Retriever paper, which originally filtered false negatives during hard negative sampling.
 We adapt this to in-batch negatives, treating false negatives as dynamic samples guided by margin-based filtering.
+<img src="https://cdn-uploads.huggingface.co/production/uploads/642b0c2fecec03b4464a1d9b/Orr03zyVerBU_B6Vkesgl.png" width="800"/>
 The sentence-transformers library now supports GISTEmbedLoss with margin configuration, making it easy to integrate into any training pipeline.