Sehyun Choi (syncdoth)

syncdoth

Geek Repo

Location:South Korea | Hong Kong

Home Page:syncdoth.github.io

Twitter:@schoiaj

Github PK Tool:Github PK Tool

Sehyun Choi's starred repositories

llm.c

LLM training in simple, raw C/CUDA

Language:CudaLicense:MITStargazers:20596Issues:0Issues:0

pyhgf

PyHGF: A neural network library for predictive coding

Language:PythonLicense:GPL-3.0Stargazers:40Issues:0Issues:0

predictive-forward-forward

Implementation/simulation of the predictive forward-forward credit assignment algorithm for training neurobiologically-plausible recurrent neural network models.

Language:PythonLicense:MITStargazers:52Issues:0Issues:0
Language:PythonLicense:Apache-2.0Stargazers:1982Issues:0Issues:0

LLM-Shearing

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

Language:PythonLicense:MITStargazers:480Issues:0Issues:0

Awesome-LLM-KG

Awesome papers about unifying LLMs and KGs

Stargazers:1715Issues:0Issues:0

pykan

Kolmogorov Arnold Networks

Language:Jupyter NotebookLicense:MITStargazers:13093Issues:0Issues:0

litgpt

Pretrain, finetune, deploy 20+ LLMs on your own data. Uses state-of-the-art techniques: flash attention, FSDP, 4-bit, LoRA, and more.

Language:PythonLicense:Apache-2.0Stargazers:7704Issues:0Issues:0

miner-release

Stable Diffusion and LLM miner for Heurist

Language:PythonLicense:NOASSERTIONStargazers:34Issues:0Issues:0

grok-1

Grok open release

Language:PythonLicense:Apache-2.0Stargazers:48994Issues:0Issues:0

Sophia

The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”

Language:PythonLicense:MITStargazers:906Issues:0Issues:0

flash-linear-attention

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

Language:PythonLicense:MITStargazers:596Issues:0Issues:0

safari

Convolutions for Sequence Modeling

Language:AssemblyLicense:Apache-2.0Stargazers:842Issues:0Issues:0

axolotl

Go ahead and axolotl questions

Language:PythonLicense:Apache-2.0Stargazers:6516Issues:0Issues:0

BitNet

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

Language:PythonLicense:MITStargazers:1387Issues:0Issues:0

mergekit

Tools for merging pretrained large language models.

Language:PythonLicense:LGPL-3.0Stargazers:3826Issues:0Issues:0

nanotron

Minimalistic large language model 3D-parallelism training

Language:PythonLicense:Apache-2.0Stargazers:899Issues:0Issues:0

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Language:PythonLicense:Apache-2.0Stargazers:1637Issues:0Issues:0

hivemind

Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.

Language:PythonLicense:MITStargazers:1855Issues:0Issues:0

DoLa

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

Language:PythonStargazers:355Issues:0Issues:0

pretraining

Pretraining

Language:PythonLicense:MITStargazers:14Issues:0Issues:0

TransformerLens

A library for mechanistic interpretability of GPT-style language models

Language:PythonLicense:MITStargazers:1038Issues:0Issues:0

lmql

A language for constraint-guided and efficient LLM programming.

Language:PythonLicense:Apache-2.0Stargazers:3427Issues:0Issues:0

outlines

Structured Text Generation

Language:PythonLicense:Apache-2.0Stargazers:6551Issues:0Issues:0

guidance

A guidance language for controlling large language models.

Language:Jupyter NotebookLicense:MITStargazers:17910Issues:0Issues:0

NeMo-Guardrails

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

Language:PythonLicense:NOASSERTIONStargazers:3601Issues:0Issues:0

mamba

Mamba SSM architecture

Language:PythonLicense:Apache-2.0Stargazers:10946Issues:0Issues:0

FilmstripMaker

c++ Program for adding images together into a film strip. Useful in creating GUIs

Language:C++License:MITStargazers:5Issues:0Issues:0

honest_llama

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Language:PythonLicense:MITStargazers:371Issues:0Issues:0

Knowledge-Constrained-Decoding

Official Code for EMNLP2023 Main Conference paper: "KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection"

Language:PythonStargazers:25Issues:0Issues:0