Sublime

2-5x faster 50% less memory local LLM finetuning

• Manual autograd engine - hand derived backprop steps.


• 2x to 5x faster than QLoRA. 50% less memory usage.


• All kernels written in OpenAI's Triton language.


• 0% loss in accuracy - no approximation methods - all exact.


• No change of hardware necessary. Supports NVIDIA GPUs since 2018+. Minimum CUDA Compute Cap

... See more

DAOs work best when the governance burden related to curation, security, and risk can be reduced faster than the natural increase in coordination costs that accompanies the need to have members involved in voting on every decision made.

Stable Beluga 2

Use Stable Chat (Research Preview) to test Stability AI's best language models for free

Model Description

Stable Beluga 2 is a Llama2 70B model finetuned on an Orca style Dataset

What is Pingora

Pingora is a Rust framework to build fast, reliable and programmable networked systems.

Pingora is battle tested as it has been serving more than 40 million Internet requests per second for more than a few years.

Pods are Orca Protocol’s answer to the scaling problems that DAOs face. Pods are small working groups, usually centered around one expertise. In place of—or in addition to—one massive, centralized DAO treasury, each pod has its own multi-sig wallet that is controlled by the pod members. So pods can be thought of as mini-DAOs within a larger DAO.

LoRAX (LoRA eXchange) is a framework that allows users to serve thousands of fine-tuned models on a single GPU, dramatically reducing the cost of serving without compromising on throughput or latency.

📖 Table of contents

• 📖 Table of contents


• 🌳 Features


• 🏠 Models


• 🏃‍♂️ Getting started with Docker
  
  
  • Launch LoRAX Server
  
  
  • Prompt via REST API
  
  
  • Prompt via Python

... See more