xu3kev

llm.c

LLM training in simple, raw C/CUDA

tmuxinator

Manage complex tmux sessions easily

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

zsh-vi-mode

💻 A better and friendly vi(vim) mode plugin for ZSH.

auto-code-rover

A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 30.67% tasks (pass@1) in SWE-bench lite with each task costs less than $0.7.

schedule_free

Schedule-Free Optimization in PyTorch

torchtitan

A native PyTorch Library for large model training

gpu_poor

Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization

llm-transparency-tool

LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/llm-transparency-tool-demo

quanto

A pytorch Quantization Toolkit

7900xtx

Sensei

Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI

LiveCodeBench

Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"

loom

a socketteer/loom reimplementation in obsidian

speechless

LLM based agents with proactive interactions, long-term memory, external tool integration, and local deployment capabilities.

compfiles

Catalog Of Math Problems Formalized In Lean

emaillm

MMOS

Mix of Minimal Optimal Sets (MMOS) of dataset has two advantages for two aspects, higher performance and lower construction costs on math reasoning.

evol-dataset

evol augment any dataset online

turing

Turing machines, Rule 110, and A::B reversal using Claude 3 Opus.

MuKoe

docker-nginx-openai-api-cache

A nginx and docker built reverse proxy server to cache the slow expensive requests to the openai api.

gpt-accelera

Simple and efficient pytorch-native transformer training and inference (batched)

ab_challenge_eval

Evaluator for the A::B Prompting Challenge

LeanCourse23

synchromesh

Get language models to generate responses in a specific format reliably. Open source implementation of Synchromesh: Reliable code generation from pre-trained language models.

regal_program_learning

llm.c

LLM training in simple, raw C/CUDA

QDSyntheticData

LambdaBeam