Prithiv Sakthi's picture

Prithiv Sakthi

prithivMLmods

·

https://huggingface.co/strangerzonehf

AI & ML interests

computer vision, multimodality, adapters @starngerzonehf @strangerguardhf

Recent Activity

upvoted an article about 1 hour ago

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

reacted to lysandre's post with 🔥 about 1 hour 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 ❤️ about 1 hour 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

prithivMLmods's activity

upvoted an article about 1 hour ago

Article

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

4 days ago

• 86

upvoted 2 collections 1 day ago

DeepSeek

11 items • Updated 3 days ago • 3

The Ultimate Collection of Code Classifiers

🔥 15 classifiers, 124M parameters, one per programming language— for assessing the educational value of GitHub code • 15 items • Updated 1 day ago • 9

upvoted a paper 1 day ago

Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published 2 days ago • 127

upvoted an article 2 days ago

Article

Fixing Open LLM Leaderboard with Math-Verify

8 days ago

• 24

upvoted a collection 2 days ago

Deepfake Classification 022025

based on recent dataset • 5 items • Updated 1 day ago • 8

upvoted a collection 3 days ago

Deepfake Quality Assessment

Controllable Classification of Good and Bad Quality Deepfakes • 6 items • Updated about 3 hours ago • 5

upvoted an article 4 days ago

Article

Fine-tuning SmolLM with Group Relative Policy Optimization (GRPO) by following the Methodologies

By

•

4 days ago

• 15

upvoted a collection 4 days ago

Image Annotation & Captioning

Trained based on Flux-generated images and their enhanced prompt captioning and annotations in a simple JSON format. • 3 items • Updated 4 days ago • 10

upvoted 3 collections 8 days ago

Deepfake Quality Assess Datasets

Classification of Good and Bad Quality Deepfakes { Datasets } • 4 items • Updated 8 days ago • 5

Purposeful Conversational Models 🚅

providing assistance • 7 items • Updated about 6 hours ago • 10

Coder Models Equilibrium 🧑🏻‍💻

Coder Models • 3 items • Updated about 7 hours ago • 8

upvoted a collection 10 days ago

Reasoning is all you need 🌠

The garage for 14B and 7B reasoning models, listed based on benchmarks. • 24 items • Updated 9 days ago • 9

upvoted 2 articles 11 days ago

Article

Open R1: Update #2

By

and 6 others •

11 days ago

• 181

Article

Fine-tune Deepseek-R1 with a Synthetic Reasoning Dataset

By

•

11 days ago

• 35

upvoted 2 collections 11 days ago

Vision Infer Custom

VLM - Multimodality • 2 items • Updated 27 days ago • 8

Reasoning Exp Domain Models 🧠

Based on Qwen's 2 vL • 2 items • Updated 11 days ago • 7

upvoted a paper 14 days ago

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

Paper • 2502.02737 • Published 17 days ago • 187

upvoted a paper 15 days ago

LIMO: Less is More for Reasoning

Paper • 2502.03387 • Published 16 days ago • 56

upvoted an article 16 days ago

Article

Agentic RAG Stack (2/5) - Augment retrieval results by reranking using Sentence Transformers

By

•

16 days ago

• 9