Vaibhav Srivastav's picture

Vaibhav Srivastav PRO

reach-vb

·

https://vaibhavs10.github.io

AI & ML interests

TTS + LM performance prediction

Recent Activity

replied to lysandre's post 1 day ago

SmolVLM-2 and SigLIP-2 are now part of `transformers` in dedicated releases! They're added on top of the v4.49.0 release, and can be installed from the following tags: `v4.49.0-SmolVLM-2` and `v4.49.0-SigLIP-2`. This marks a new beginning for the release process of transformers. For the past five years, we've been doing monthly releases featuring many models (v4.49.0, the latest release, features 9 new architectures). Starting with SmolVLM-2 & SigLIP2, we'll now additionally release tags supporting new models on a stable branch. These models are therefore directly available for use by installing from the tag itself. These tags will continue to be updated with fixes applied to these models. Going forward, continue expecting software releases following semantic versioning: v4.50.0 will have ~10 new architectures compared to v4.49.0, as well as a myriad of new features, improvements and bug fixes. Accompanying these software releases, we'll release tags offering brand new models as fast as possible, to make them accessible to all immediately.

reacted to lysandre's post with 🚀 1 day ago

SmolVLM-2 and SigLIP-2 are now part of `transformers` in dedicated releases! They're added on top of the v4.49.0 release, and can be installed from the following tags: `v4.49.0-SmolVLM-2` and `v4.49.0-SigLIP-2`. This marks a new beginning for the release process of transformers. For the past five years, we've been doing monthly releases featuring many models (v4.49.0, the latest release, features 9 new architectures). Starting with SmolVLM-2 & SigLIP2, we'll now additionally release tags supporting new models on a stable branch. These models are therefore directly available for use by installing from the tag itself. These tags will continue to be updated with fixes applied to these models. Going forward, continue expecting software releases following semantic versioning: v4.50.0 will have ~10 new architectures compared to v4.49.0, as well as a myriad of new features, improvements and bug fixes. Accompanying these software releases, we'll release tags offering brand new models as fast as possible, to make them accessible to all immediately.

reacted to lysandre's post with ❤️ 1 day ago

SmolVLM-2 and SigLIP-2 are now part of `transformers` in dedicated releases! They're added on top of the v4.49.0 release, and can be installed from the following tags: `v4.49.0-SmolVLM-2` and `v4.49.0-SigLIP-2`. This marks a new beginning for the release process of transformers. For the past five years, we've been doing monthly releases featuring many models (v4.49.0, the latest release, features 9 new architectures). Starting with SmolVLM-2 & SigLIP2, we'll now additionally release tags supporting new models on a stable branch. These models are therefore directly available for use by installing from the tag itself. These tags will continue to be updated with fixes applied to these models. Going forward, continue expecting software releases following semantic versioning: v4.50.0 will have ~10 new architectures compared to v4.49.0, as well as a myriad of new features, improvements and bug fixes. Accompanying these software releases, we'll release tags offering brand new models as fast as possible, to make them accessible to all immediately.

View all activity

Organizations

reach-vb's activity

upvoted a paper 2 days ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published 3 days ago • 96

upvoted an article 2 days ago

Article

SigLIP 2: A better multilingual vision language encoder

2 days ago

• 69

upvoted a paper 3 days ago

Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published 4 days ago • 134

upvoted an article 3 days ago

Article

SmolVLM2: Bringing Video Understanding to Every Device

3 days ago

• 133

upvoted a paper 3 days ago

Presumed Cultural Identity: How Names Shape LLM Responses

Paper • 2502.11995 • Published 6 days ago • 9

upvoted an article 4 days ago

Article

PaliGemma 2 Mix - New Instruction Vision Language Models by Google

4 days ago

• 53

upvoted a collection 4 days ago

PaliGemma 2 Mix

13 items • Updated 4 days ago • 54

upvoted 2 articles 5 days ago

Article

Introducing Three New Serverless Inference Providers: Hyperbolic, Nebius AI Studio, and Novita 🔥

5 days ago

• 87

Article

Welcome Fireworks.ai on the Hub 🎆

9 days ago

• 52

upvoted a paper 10 days ago

Scaling Pre-training to One Hundred Billion Data for Vision Language Models

Paper • 2502.07617 • Published 12 days ago • 27

upvoted an article 10 days ago

Article

From Chunks to Blocks: Accelerating Uploads and Downloads on the Hub

11 days ago

• 48

upvoted a collection 12 days ago

OLMoE (January 2025)

Improved OLMoE for iOS app. Read more: https://allenai.org/blog/olmoe-app • 10 items • Updated 12 days ago • 9

upvoted an article 12 days ago

Article

From Llasa to Llasagna 🍕: Finetuning LLaSA to generates Italian speech and other languages

By

and 1 other •

12 days ago

• 22

upvoted an article 13 days ago

Article

Open R1: Update #2

By

and 6 others •

13 days ago

• 183

upvoted a paper 16 days ago

High-Fidelity Simultaneous Speech-To-Speech Translation

Paper • 2502.03382 • Published 18 days ago • 8

upvoted a collection 17 days ago

Hibiki fr-en

Hibiki is a model for streaming speech translation , which can run on device! See https://github.com/kyutai-labs/hibiki. • 5 items • Updated 16 days ago • 49

upvoted 2 papers 17 days ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published 18 days ago • 188

Fully Autonomous AI Agents Should Not be Developed

Paper • 2502.02649 • Published 18 days ago • 23

upvoted 2 articles 18 days ago

Article

π0 and π0-FAST: Vision-Language-Action Models for General Robot Control

19 days ago

• 106

Article

Open-source DeepResearch – Freeing our search agents

19 days ago

• 1.08k