davide221

manim

Animation engine for explanatory math videos

LLM101n

LLM101n: Let's build a Storyteller

abliterator

Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens

TransformerLens

A library for mechanistic interpretability of GPT-style language models

short-transformers

Prune transformer layers

RemoteCLIP

🛰️ Official repository of paper "RemoteCLIP: A Vision Language Foundation Model for Remote Sensing" (IEEE TGRS)

oss-cad-suite-build

Multi-platform nightly builds of open source digital design and verification tools

Awesome-Code-LLM

A curated list of language modeling researches for code and related datasets.

Awesome-LLM4EDA

axolotl

Go ahead and axolotl questions

GPTFast

Accelerate your Hugging Face Transformers 7.6-9x. Native to Hugging Face and PyTorch.

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

inkdrop-visualizer

Visualizes your Terraform

LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

ComfyUI

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

laser

The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

alphageometry

alpaca_eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Tensor-Puzzles

Solve puzzles. Improve your pytorch.

megablocks

minRLHF

A (somewhat) minimal library for finetuning language models with PPO on human feedback.

text-embeddings-inference

A blazing fast inference solution for text embeddings models

optimum-nvidia

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

gpt-crawler

Crawl a site to generate knowledge files to create your own custom GPT from a URL

AutoAWQ

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

attention_sinks

Extend existing LLMs way beyond the original training length with constant memory usage, without retraining

worker-tgi

The RunPod worker template for serving our large language model endpoints. Powered by Text Generation Inference.

DS-1000

[ICML 2023] Data and code release for the paper "DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation".