Tools for merging pretrained large language models.

Lord of LLMS

Go ahead and axolotl questions

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

Falcon LLM ggml framework with CPU and GPU support

TheBloke's Dockerfiles

A discord bot with many features which uses A1111 as backend and uses my prompt templates for beautiful generations - even with short prompts.

Python bindings for the Transformer models implemented in C/C++ using GGML library.

LLM inference in C/C++

Universal LLM Deployment Engine with ML Compilation

Python bindings for llama.cpp

A Gradio web UI for Large Language Models with support for multiple inference backends.

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

4 bits quantization of LLaMA using GPTQ

Run LLaMA (and Stanford-Alpaca) inference on Apple Silicon GPUs.

Install nVidia drivers on macOS the easy way.

No longer maintained, see pinned issues

A PEX to Papyrus Decompiler for Skyrim, Fallout 4 and Starfield

Mod manager for various PC games (currently: Skyrim, Oblivion, Fallout 3, Fallout NV)

Everything here is old and outdated by at least 5 years.

The stack_unwinding is a small header only C++ library which supplies primitive(class unwinding_indicator) to determining when object destructor is called due to stack-unwinding or due to normal sc…

Python parser for Paradox .txt files.

Compute Napoleon Score for Europa Universalis IV

Battle Simulator for Europa Universalis 4