Trending

[R] Vision Transformers Don't Need Trained Registers

ArchGW 0.3.2 | First class support for routing to Gemini-based LLMs and Hermes - an extension framework to add new LLMs with ease

[R] Analyzing paths datapoints take through clustered latent space with LLMs

[P] Non Diverse predictions for Time Series Custom Transformer using global Zscore and RevIn

Google and Microsoft vs OpenAI and Anthropic, a fun visualization of their open releases on Hugging Face in the past year (Julien Chaumond on LinkedIn)

[D] About spatial reasoning VLMs

[R] Text-to-LoRA: Instant Transformer Adaption

mistralai/Magistral-Small-2506

[D] Best papers explaining how transformer based LLMs really work internally

OpenBMB

Save item

MiniCPM4-8B

Task: text-generation

Centro de Excelência em IA

Save item

Gemma-3-Gaia-PT-BR-4b-it

Task: image-text-to-text

H company

Save item

Holo1-7B

Task: image-text-to-text

Qwen

Save item

Qwen3-Reranker-0.6B

Task: text-generation

Qwen

Save item

Qwen3-Reranker-8B

Task: text-generation

Qwen

Save item

Qwen3-Reranker-4B

Task: text-ranking

Google

Save item

medgemma-4b-it

Task: image-text-to-text

Xiaomi MiMo

Save item

MiMo-VL-7B-RL

Task: image-text-to-text

H company

Save item

Holo1-3B

Task: image-text-to-text

huggingface

Save item

transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

WongKinYiu

Save item

yolov7

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

microsoft

Save item

Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

NVIDIA

Save item

Megatron-LM

Ongoing research training transformer models at scale

huggingface

Save item

optimum

🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

lucidrains

Save item

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch