Suraj's picture

21 63

Suraj

ghishadow

·

AI & ML interests

None yet

Recent Activity

liked a model 8 days ago

LiquidAI/LFM2-2.6B-Exp

liked a model 22 days ago

Qwen/Qwen3-VL-2B-Thinking

liked a model 28 days ago

moonshotai/Kimi-Linear-48B-A3B-Instruct

View all activity

Organizations

upvoted a collection about 1 month ago

Ministral 3

Mistral Ministral 3: new multimodal models in Base, Instruct, and Reasoning variants, available in 3B, 8B, and 14B sizes. • 36 items • Updated 11 days ago • 26

upvoted a paper 2 months ago

Latent Diffusion Model without Variational Autoencoder

Paper • 2510.15301 • Published Oct 17, 2025 • 49

upvoted an article 4 months ago

Article

The Hacker's Guide to Building an AI Supercluster

Aug 31, 2025

•

7

upvoted a collection 5 months ago

Gemma 3-270m

Collection of models for Gemma 3-270m • 4 items • Updated 19 days ago • 21

upvoted a paper 5 months ago

CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning

Paper • 2507.14111 • Published Jul 18, 2025 • 23

upvoted a collection 10 months ago

olmOCR

olmOCR is a document recognition pipeline for efficiently converting documents into plain text. olmocr.allenai.org • 12 items • Updated 11 days ago • 140

upvoted a paper 12 months ago

Evolving Deeper LLM Thinking

Paper • 2501.09891 • Published Jan 17, 2025 • 115

upvoted a collection 12 months ago

Gemma Scope Release

A comprehensive, open suite of sparse autoencoders for Gemma 2 2B and 9B. • 10 items • Updated Jul 10, 2025 • 20

upvoted 2 papers about 1 year ago

Byte Latent Transformer: Patches Scale Better Than Tokens

Paper • 2412.09871 • Published Dec 13, 2024 • 108

Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference

Paper • 2412.13663 • Published Dec 18, 2024 • 158

upvoted a collection about 1 year ago

ModernBERT

Bringing BERT into modernity via both architecture changes and scaling • 3 items • Updated Dec 19, 2024 • 152

upvoted an article over 1 year ago

Article

SmolLM - blazingly fast and remarkably powerful

+1

Jul 16, 2024

•

436

upvoted a paper over 1 year ago

An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion

Paper • 2408.03178 • Published Aug 6, 2024 • 40

upvoted an article over 1 year ago

Article

How to generate text: using different decoding methods for language generation with Transformers

Mar 1, 2020

•

279

upvoted a paper over 1 year ago

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 627

upvoted 3 articles over 1 year ago

Article

A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes

Aug 17, 2022

•

122

Article

Unbelievable! Run 70B LLM Inference on a Single 4GB GPU with This NEW Technique

Nov 30, 2023

•

34

Article

PaliGemma – Google's Cutting-Edge Open Vision Language Model

+1

May 14, 2024

•

278

upvoted a collection over 1 year ago

Llama 3

8 items • Updated Apr 18, 2024 • 15

upvoted a collection almost 2 years ago

Qwen1.5

Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. • 55 items • Updated 4 days ago • 211