Trending

R0ML's Ratio

GPT-5: Overdue, overhyped and underwhelming. And that's not the worst of it

Don Knuth on ChatGPT(07 April 2023)

Getting Good Results from Claude Code

Gptoss120B – OpenAI Open Source Large Language Model GPT-OSS-120B Official Site

The surprise deprecation of GPT-4o for ChatGPT consumers

How Attention Sinks Keep Language Models Stable

GPT 5 vs. Opus 4.1 for Vibe-Coded Apps

FLUX.1-Krea and the Rise of Opinionated Models

[R] Plain English outperforms JSON for LLM tool calling: +18pp accuracy, -70% variance

RTX Pro 6000 Blackwell vLLM Benchmark: 120B Model Performance Analysis

Using llamacpp and RCP, managed to improve promt processing by 4x times (160 t/s to 680 t/s) and text generation by 2x times (12.67 t/s to 22.52 t/s) by changing the device order including RPC. GLM 4.6 IQ4_XS multiGPU + RPC.

Meta just dropped MobileLLM-Pro, a new 1B foundational language model on Huggingface

We built 3B and 8B models that rival GPT-5 at HTML extraction while costing 40-80x less - fully open source

Google C2S-Scale 27B (based on Gemma) built with Yale generated a novel hypothesis about cancer cellular behavior - Model + resources are now on Hugging Face and GitHub

Qwen3-30B-A3B FP8 on RTX Pro 6000 blackwell with vllm

[R]: Create a family of pre-trained LLMs of intermediate sizes from a single student-teacher pair

Qwen3-VL-4B and 8B Instruct & Thinking are here

Microsoft

Save item

UserLM-8b

Task: text-generation

Qwen

Save item

Qwen3-VL-8B-Instruct

Task: image-text-to-text

Z.ai

Save item

GLM-4.6

Task: text-generation

Qwen

Save item

Qwen3-VL-4B-Instruct

Task: image-text-to-text

Van Dijk Lab @ Yale

Save item

C2S-Scale-Gemma-2-27B

Task: text-generation

KORMo

Save item

KORMo-10B-sft

Task: text-generation

Qwen

Save item

Qwen3-VL-8B-Thinking

Task: image-text-to-text

Qwen

Save item

Qwen3-VL-30B-A3B-Instruct

VNGRS

Save item

Kumru-2B

Task: text-generation

Dao-AILab

Save item

flash-attention

Fast and memory-efficient exact attention

run-llama

Save item

llama_index

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

deepspeedai

Save item

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

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.

NVIDIA

Save item

Megatron-LM

Ongoing research training transformer models at scale

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

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

ggml-org

Save item

whisper.cpp

Port of OpenAI's Whisper model in C/C++

WongKinYiu

Save item

yolov7

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