alpindale Goto Github PK

alpindale

Config files for my GitHub profile.

auroranemoia.github.io

My cool portfolio website, it will one day be built with Astro...

autoquarot

Auto convert transformers models to QuaRot.

autoquip

Easy to use LLM quantization via the QuIP# technique

axolotl

Go ahead and axolotl questions

c-practice

Stuff I learn.

causal-lm-lora

Training code for training LoRAs

causal_llm_tuning

Jupyter notebook for when I want to quickly tune a causal LLM

cyberpunk-grub-theme-ultrawide

Cyberpunk 2077 Grub Theme - Ultrawide

dynarmic

Dynamic ARM Re-compiler.

epubtoraw

A little tool made to convert epub files to raw text.

exllamav2

A fast inference library for running LLMs locally on modern consumer-class GPUs

flash-attention-rocm

Fast and memory-efficient exact attention

galatea-frontend

gpt-j_int4_lora

Code for fine-tuning GPT-J LoRAs in 4bit

gptq-for-llama

4 bits quantization of LLaMa using GPTQ

gptq-gptj

Code for the paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers" with GPT-J implementation.

gptslop

A community list of common phrases generated by GPT and Claude models

grok-1

Grok open release

interactive-tutorials

Interactive Tutorials

koboldai

landmark-attention

Landmark Attention: Random-Access Infinite Context Length for Transformers

langchain

⚡ Building applications with LLMs through composability ⚡

legion

The Legion Parallel Programming System

litellm

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

llama.cpp

Port of Facebook's LLaMA model in C/C++

llm-shearing

Preprint: Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

lora-merge

Script for merging LoRA adapters with base models.

marlin

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

mergekit

Tools for merging pretrained large language models.