codes documenting my gpu learning journey

MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user develop their prompts into full models.

SimpleHTTPServer with support for Range requests

Go ahead and axolotl questions

Python bindings for llama.cpp

A Simple webserver for generating text with exllamav2

Command-line script for inferencing from models such as falcon-7b-instruct

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

Use context-free grammars with an LLM

Exact structure out of any language model completion.

4 bits quantization of LLaMA using GPTQ

This repository contains the collection of explorative notebooks pure in python and in the language that we, humans can read. Have tried to compile all lectures from the Andrej Karpathy's 💎 playlis…

how to write lots of quines

JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.

GPT Experiments

Language model alignment-focused deep learning curriculum

A minimal code example that trains a neural network for MNIST classification from scratch

gpt.sh

Dmitry Grinberg: Using RP2040 PIO to drive a poorly-designed display

Neural ngram language model in PyTorch.

A Python app that generates Pokemon cards, and uses GPT and Midjourney for flavor.

Paper List for In-context Learning 🌷

notes for software engineers getting up to speed on new AI developments. Serves as datastore for https://latent.space writing, and product brainstorming, but has cleaned up canonical references und…

ripgrep recursively searches directories for a regex pattern while respecting your gitignore

Python packaging and dependency management made easy

Web-based XMPP/Jabber chat written in JavaScript

A Syntax highlighting extension for the goldmark markdown parser.