Stories by jmorgan

UI-TARS-1.5: open-source computer use vision-language model

Diffusion models are real-time game engines

Sheared LLaMA: Accelerating Language Model Pre-Training via Structured Pruning

Unexpected Baskerville: The Story of LoveFrom Serif [video]

Ollama for Linux – Run LLMs on Linux with GPU Acceleration

Efficient Memory Management for Large Language Model Serving with PagedAttention

Prompting Code Llama

Falcon 180B

Run Code Llama Locally

WizardMath solves math problems with Llama 2

PrivateGPT with Llama 2 Uncensored

Run Llama 2 uncensored locally

Show HN: Ollama – Run LLMs on your Mac

TaskMatrix

The Path to Self-Sovereign Identity

The Linux Kernel Key Retention Service and why you should use it

Launch HN: Infra (YC W21) – Open-source access management for Kubernetes

Halide Mark II

Filecoin Mainnet Is Live

U-2 Federal Lab achieves flight with Kubernetes

1