ColBERTv2.0-spanish-mmarcoES

AdrienB134/ColBERTv2.0-spanish-mmarcoES

ColBERTv2.0-spanish-mmarcoES is a machine learning model from AdrienB134. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.

Downloads · 30 days

0% of all-time downloads

All-time downloads

771K

Public

Parameters

110M

440 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors440 MB · 100%

At a glance

Library: transformers
License: mit
Model type: bert
Access: Public
Created: Feb 27, 2024
Updated: Feb 27, 2024
SHA: 2f41edb4

Datasets

unicamp-dl/mmarco

Model card

From the Hugging Face model README

Training

Details

The model is initialized from the ColBERTv1.0-bert-based-spanish-mmarcoES checkpoint and trained using the ColBERTv2 style of training.
It was trained on 2 Tesla T4 GPU with 16GBs of memory each with 20k warmup steps warmup using a batch size of 64 and the AdamW optimizer with a constant learning rate of 1e-05. Total training time was around 60 hours.

Data

The model is fine-tuned on the Spanish version of the mMARCO dataset, a multi-lingual machine-translated version of the MS MARCO dataset.

Evaluation

The model is evaluated on the smaller development set of mMARCO-es, which consists of 6,980 queries for a corpus of 8.8M candidate passages. We report the mean reciprocal rank (MRR) and recall at various cut-offs (R@k).

model	Vocab.	#Param.	Size	MRR@10	R@50	R@1000
ColBERTv2.0-spanish-mmarcoES	spanish	110M	440MB	32.86	76.46	81.06
ColBERTv1.0-bert-based-spanish-mmarcoES	spanish	110M	440MB	24.70	59,23	63.86

Library: transformers
Type: bert
License: mit
Languages: es
Created: Feb 27, 2024
Updated: Feb 27, 2024