katanallama

katanallama's Stars

• tecosaur/org-pandoc-import

  Mirror of https://git.tecosaur.net/tec/org-pandoc-import

  Language:Emacs Lisp24514

• alekseysidorov/nixpkgs-cross-overlay

  Language:Nix174

• tvlfyi/tvix

  Tvix - A Rust implementation of Nix. Read-only mirror of https://cs.tvl.fyi/depot/-/tree/tvix

  Language:Rust6778

• willbush/system

  Trying to build the perfect system

  Language:Emacs Lisp583

• stm32-rs/stm32-rs

  Embedded Rust device crates for STM32 microcontrollers

  Language:Python1.3k224

• karpathy/llama2.c

  Inference Llama 2 in one file of pure C

  Language:C17.5k2.1k

• DeterminateSystems/magic-nix-cache-action

  Save 30-50%+ of CI time without any effort or cost. Use Magic Nix Cache, a totally free and zero-configuration binary cache for Nix on GitHub Actions.

  Language:TypeScript39415

• numtide/nix-gl-host

  Run OpenGL/Cuda programs built with Nix, on all Linux distributions.

  Language:Python8216

• nix-community/nixGL

  A wrapper tool for nix OpenGL application [maintainer=@guibou]

  Language:Nix71080

• tuhhosg/reupnix

  Reconfigurable and Updateable Embedded Systems

  Language:Shell292

• artidoro/qlora

  QLoRA: Efficient Finetuning of Quantized LLMs

  Language:Jupyter Notebook10k821

• zylon-ai/private-gpt

  Interact with your documents using the power of GPT, 100% privately, no data leaks

  Language:Python54.1k7.3k

• lucidrains/MEGABYTE-pytorch

  Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch

  Language:Python62452

• qwopqwop200/GPTQ-for-LLaMa

  4 bits quantization of LLaMA using GPTQ

  Language:Python3k457

• UX-Decoder/Segment-Everything-Everywhere-All-At-Once

  [NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

  Language:Python4.4k400

• ggerganov/ggml

  Tensor library for machine learning

  Language:C++11.2k1k

• yoheinakajima/babyagi

  Language:Python20.4k2.7k

• microsoft/LoRA

  Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

  Language:Python10.7k685

• huggingface/trl

  Train transformer language models with reinforcement learning.

  Language:Python10k1.3k

• nixified-ai/flake

  A Nix flake for many AI projects

  Language:Nix67173

• tysam-code/hlb-gpt

  Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wikitext-103 on a single A100 in <100 seconds. Scales to larger models with one parameter change (feature currently in alpha).

  Language:Python33227

• michaelgutmann/ml-pen-and-paper-exercises

  Pen and paper exercises in machine learning

  Language:TeX1.9k141

• IST-DASLab/sparsegpt

  Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".

  Language:Python71696

• openai/chatgpt-retrieval-plugin

  The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

  Language:Python21.1k3.7k

• ggerganov/llama.cpp

  LLM inference in C/C++

  Language:C++67.8k9.7k

• tloen/alpaca-lora

  Instruct-tune LLaMA on consumer hardware

  Language:Jupyter Notebook18.6k2.2k

• antimatter15/alpaca.cpp

  Locally run an Instruction-Tuned Chat-Style LLM

  Language:C10.3k906

• bitsandbytes-foundation/bitsandbytes

  Accessible large language models via k-bit quantization for PyTorch.

  Language:Python6.3k631

• tatsu-lab/stanford_alpaca

  Code and documentation to train Stanford's Alpaca models, and generate the data.

  Language:Python29.5k4.1k

• Dao-AILab/flash-attention

  Fast and memory-efficient exact attention

  Language:Python14.2k1.3k