Dayan Ruben

dayanruben's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 collections 1 day ago

Gemma Family

Collection

LiteRT models in the Gemma Family • 12 items • Updated 7 days ago • 28

MiniMax-M1

Collection

MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. • 6 items • Updated Oct 21 • 119

upvoted 18 collections 7 days ago

Google's Gemma models family

Collection

332 items • Updated 7 days ago • 633

Gemma 2 JPN Release

Collection

A Gemma 2 2B model fine-tuned on Japanese text. It supports the Japanese language the same level of performance of EN only queries on Gemma 2. • 3 items • Updated Jul 10 • 30

TimesFM Release

Collection

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting. • 6 items • Updated Oct 4 • 29

Gemma-APS Release

Collection

Gemma models for text-to-propositions segmentation. The models are distilled from fine-tuned Gemini Pro model applied to multi-domain synthetic data. • 3 items • Updated Jul 10 • 24

ImageInWords Release

Collection

arXiv: https://arxiv.org/abs/2405.02793 • 3 items • Updated Jul 10 • 4

IndicGenBench

Collection

Datasets released in "IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs" (https://arxiv.org/abs/2404.16816) • 4 items • Updated Jul 10 • 11

SigLIP

Collection

Contrastive (sigmoid) image-text models from https://arxiv.org/abs/2303.15343 • 10 items • Updated Jul 10 • 62

Switch-Transformers release

Collection

This release included various MoE (Mixture of expert) models, based on the T5 architecture . The base models use from 8 to 256 experts. • 9 items • Updated Jul 10 • 18

SEAHORSE release

Collection

The SEAHORSE metrics (as described in https://arxiv.org/abs/2305.13194). • 12 items • Updated Jul 10 • 20

MT5 release

Collection

The MT5 release follows the T5 family, but is pretrained on multilingual data. The update UMT5 models are pretrained on an updated corpus. • 10 items • Updated Jul 10 • 23

T5 release

Collection

The original T5 transformer release was done in two steps, the original T5 checkpoints and the improved T5v1 • 9 items • Updated Jul 10 • 17

Flan-T5 release

Collection

The Flan-T5 covers 4 checkpoints of different sizes each time. It also includes upgrades versions trained using Universal sampling • 7 items • Updated Jul 10 • 30

ELECTRA release

Collection

This collection regroups the ELECTRA models released by the Google team. • 6 items • Updated Jul 10 • 12

ALBERT release

Collection

The ALBERT release was done in two steps, over 4 checkpoints of different sizes each time. The first version is noted as "v1", the second as "v2". • 8 items • Updated Jul 10 • 7

BERT release

Collection

Regroups the original BERT models released by the Google team. Except for the models marked otherwise, the checkpoints support English. • 8 items • Updated Jul 10 • 37

Gemma Scope Release

Collection

A comprehensive, open suite of sparse autoencoders for Gemma 2 2B and 9B. • 10 items • Updated Jul 10 • 19

ShieldGemma Release

Collection

A series of safety classifiers, trained on top of Gemma 2, for developers to filter inputs and outputs of their applications. • 3 items • Updated Jul 10 • 15

Gemma 2 2B Release

Collection

The 2.6B parameter version of Gemma 2. • 6 items • Updated Jul 10 • 82