koalazf99

aider

aider is AI pair programming in your terminal

seeclick-crawler

segment-anything-2

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

MAmmoTH

Code and data for "MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning" (ICLR 2024)

LoRA-GA

PDF-Extract-Kit

A Comprehensive Toolkit for High-Quality PDF Content Extraction

CompilerGym

Reinforcement learning environments for compiler and program optimization tasks

Minitron

A family of compressed models obtained via pruning and knowledge distillation

scaling-with-vocab

📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies

persona-hub

Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"

weak-to-strong-reasoning

SciCode

A benchmark that challenges language models to code solutions for scientific problems

ENVISIONS

A Neural-Symbolic Self-Training Framework

lean4game

Server to host lean games.

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

OpenWebMath

anole

Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation

regmix

🧬 RegMix: Data Mixture as Regression for Language Model Pre-training

gptpdf

Using GPT to parse PDF

Phi-3CookBook

This is a Phi-3 book for getting started with Phi-3. Phi-3, a family of open AI models developed by Microsoft. Phi-3 models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across a variety of language, reasoning, coding, and math benchmarks.

cambrian

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

flash-attention

Fast and memory-efficient exact attention

aqt

magentic

Seamlessly integrate LLMs as Python functions

remiss-jailbreak

LLM101n

LLM101n: Let's build a Storyteller

OpenRLHF

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)

DL4TP

[COLM 2024] A Survey on Deep Learning for Theorem Proving

trafilatura

Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML

Awesome-DataCentric-LLM

trending projects & awesome papers about data-centric llm studies.