joe32140
/

ColModernBERT-base-msmarco-en-bge

Sentence Similarity

sentence-transformers

feature-extraction

Generated from Trainer

dataset_size:808728

loss:Distillation

Model card Files Files and versions Community

joe32140 commited on 6 days ago

Commit

9d50a7b

•

1 Parent(s): 7c0a9e4

Update README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -52,6 +52,7 @@ tags:
 This is a [PyLate](https://github.com/lightonai/pylate) model finetuned from [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the [train](https://huggingface.co/datasets/lightonai/ms-marco-en-bge) dataset. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator.
 I finetuned the model with official script [examples/train_pylate.py](https://github.com/AnswerDotAI/ModernBERT/blob/main/examples/train_pylate.py) on a RTX 4090 GPU in 12 hours. See more details in [trianing logs](https://wandb.ai/joe32140/col-modernbert-msmarco/workspace?nw=nwuserjoe32140).
 ## Model Details

 This is a [PyLate](https://github.com/lightonai/pylate) model finetuned from [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the [train](https://huggingface.co/datasets/lightonai/ms-marco-en-bge) dataset. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator.
 I finetuned the model with official script [examples/train_pylate.py](https://github.com/AnswerDotAI/ModernBERT/blob/main/examples/train_pylate.py) on a RTX 4090 GPU in 12 hours. See more details in [trianing logs](https://wandb.ai/joe32140/col-modernbert-msmarco/workspace?nw=nwuserjoe32140).
+The finetuned model performance is on par with numbers reported in the paper.
 ## Model Details