Trending

Optimizing Tool Selection for LLM Workflows with Differentiable Programming

The Right Way to Embed an LLM in a Group Chat

Baba Is Eval

Large Language Models Are Improving Exponentially

Everything around LLMs is still magical and wishful thinking

Gremllm

VLLM: Easy, Fast, and Cheap LLM Serving with PagedAttention

Context Engineering for Agents

High-Fidelity Simultaneous Speech-to-Speech Translation

128GB VRAM for ~$600. Qwen3 MOE 235B.A22B reaching 20 t/s. 4x AMD MI50 32GB.

[d] How do I run mistral 7b locally [help

[R] Post Transformer Architecture R&D

Llama-4-Maverick 402B on a oneplus 13

Powerful 4B Nemotron based finetune

Google finds LLMs can hide secret information and reasoning in their outputs, and we may soon lose the ability to monitor their thoughts

Open source tool for generating training datasets from text files and pdf for fine-tuning language models.

Got some real numbers how llama.cpp got FASTER over last 3-months

THUDM/GLM-4.1V-9B-Thinking looks impressive

Google

Save item

gemma-3n-E4B-it

Task: image-text-to-text

Z.ai & THUKEG

Save item

GLM-4.1V-9B-Thinking

Task: image-text-to-text

Tencent

Save item

Hunyuan-A13B-Instruct

TNG Technology Consulting GmbH

Save item

DeepSeek-TNG-R1T2-Chimera

Task: text-generation

SK Telecom

Save item

A.X-4.0

Task: text-generation

BAIDU

Save item

ERNIE-4.5-21B-A3B-PT

Task: text-generation

SK Telecom

Save item

A.X-4.0-Light

Task: text-generation

K intelligence Mi:dm

Save item

Midm-2.0-Base-Instruct

Task: text-generation

BAIDU

Save item

ERNIE-4.5-0.3B-PT

Task: text-generation

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.

run-llama

Save item

llama_index

LlamaIndex is the leading framework for building LLM-powered agents over your data.

WongKinYiu

Save item

yolov7

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

NVIDIA

Save item

Megatron-LM

Ongoing research training transformer models at scale

microsoft

Save item

Swin-Transformer

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

Unstructured-IO

Save item

unstructured

Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.

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