Pull Requests huggingface/sentence-transformers

Added new MSE Similarity Evaluator

#2704 opened 2024-06-02 00:30 by DgoMndez

Add SigLIP support

#2629 opened 2024-05-06 06:21 by HonzaCuhel

Update SentenceTransformer.py to use token length for sorting

#2571 opened 2024-04-03 12:44 by achibb

Add support for M2M100EncoderModel (aka NLLB, aka SONAR text encoder)

#2541 opened 2024-03-13 22:19 by avidale

Passing arbitrary keyword arguments to submodules

#2539 opened 2024-03-12 13:51 by Markus28

Add support for asymmetric models in NoDuplicatesDataLoader

#2301 opened 2023-09-08 14:54 by eranhirs

add surprise similarity score

#2287 opened 2023-08-26 10:13 by vincentmin

Add eval_batch_size argument to cross encoder evaluators

#2284 opened 2023-08-24 18:53 by yunyu

Added move_to_cpu flag in encode method to avoid OOM for token embeddings.

#1812 opened 2023-01-19 17:00 by bodin-e

Fix Cuda out of memory issue in model.encode by allowing user to transfer to cpu

#1717 opened 2022-10-09 00:45 by Quetzalcohuatl

Add CLI and refactoring example.

#1688 opened 2022-09-08 13:10 by Yur-or

support max_seq_length argument in SentenceTransformer

#1685 opened 2022-09-07 01:54 by Jiaxin-Wen

Fetch score_function for semantic_search from model config if available

#1649 opened 2022-07-26 01:09 by NimaBoscarino

Adding the possibility to pass arguments to the AutoConfig() in the Cross-Encoder

#1421 opened 2022-02-13 21:31 by zoltan-fedor

Draft: Single layer classifier evaluator

#1385 opened 2022-01-18 20:26 by Fraser-Greenlee

Add gradient accumulation to CrossEncoder

#1092 opened 2021-08-02 12:13 by hugoabonizio

Add batch prediction to CERerankingEvaluator

#1085 opened 2021-07-29 12:06 by hugoabonizio