dockerfiles, compose files, benchmarks for 2x R9700 serving

Measures the latency between CPU cores

Make abliterated models with transformers, easy and fast

Fully automatic censorship removal for language models

Implements harmful/harmless refusal removal using pure HF Transformers

NVIDIA Linux open GPU with P2P support

Provide with pre-build flash-attention 2 and 3 package wheels on Linux and Windows using GitHub Actions

A high-throughput and memory-efficient inference and serving engine for LLMs

CUDA kernels for Don't Repeat Yourself (DRY) Sampling

Text-to-Music Generation with Rectified Flow Transformers

Text-to-Music Generation with Rectified Flow Transformer

Pursuer is a Chatbot for ArliAI.com with Unlimited AI Use!

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

Python scraper based on AI

Distribute and run LLMs with a single file.

Large-scale LLM inference engine

Go ahead and axolotl questions

Neuroengine is a service to share LLMs in the form of a webchat and API.

Translate large dataset to any language with google translation api and multithreads processing, no key required!