Trending

Text-to-LoRA: Hypernetwork that generates task-specific LLM adapters (LoRAs)

JavelinGuard: Low-Cost Transformer Architectures for LLM Security

Log-Linear Attention

Cerebras achieves 2,500T/s on Llama 4 Maverick (400B)

Tokenization for language modeling: BPE vs. Unigram Language Modeling (2020)

Domain Adaptation of Base Models + ShadowdarkQA Bench

Bagel: The Open-Source Unified Multimodal Model

Show HN: I modeled the Voynich Manuscript with SBERT to test for structure

Understanding Transformers via N-gram Statistics

[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

Sentence Transformers

Save item

all-MiniLM-L6-v2

Task: sentence-similarity

Sarvam AI

Save item

sarvam-m

Task: text-generation

LightOn AI

Save item

Reason-ModernColBERT

Task: sentence-similarity

Preferred Networks, Inc.

Save item

plamo-2-translate

Task: text-generation

Meta Llama

Save item

Llama-3.1-8B-Instruct

Task: text-generation

Google

Save item

medgemma-4b-pt

Task: image-text-to-text

NVIDIA

Save item

Cosmos-Reason1-7B

Task: image-text-to-text

Qwen

Save item

WorldPM-72B

Task: text-classification

BLIP3o

Save item

BLIP3o-Model

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