soheeyang

soheeyang's Stars

• tatsu-lab/stanford_alpaca

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

  Language:Python29.6k3422684.1k

• google-research/tuning_playbook

  A playbook for systematically maximizing the performance of deep learning models.

  27.2k286422.3k

• meta-llama/llama3

  The official Meta Llama 3 GitHub site

  Language:Python27.1k2252633.1k

• koekeishiya/yabai

  A tiling window manager for macOS based on binary space partitioning

  Language:C24k1002.1k652

• microsoft/JARVIS

  JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

  Language:Python23.7k3811812k

• openai/chatgpt-retrieval-plugin

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

  Language:Python21.1k3232313.7k

• karpathy/llama2.c

  Inference Llama 2 in one file of pure C

  Language:C17.5k1922222.1k

• huggingface/peft

  🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

  Language:Python16.4k1111.1k1.6k

• BlinkDL/RWKV-LM

  RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

  Language:Python12.7k134216862

• databrickslabs/dolly

  Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

  Language:Python10.8k1371621.2k

• OptimalScale/LMFlow

  An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

  Language:Python8.3k72410827

• openai/transformer-debugger

  Language:Python4k2514235

• TransformerLensOrg/TransformerLens

  A library for mechanistic interpretability of GPT-style language models

  Language:Python1.6k17256304

• Farama-Foundation/chatarena

  ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

  Language:Python1.4k1923131

• openai/automated-interpretability

  Language:Python9671620113

• allenai/natural-instructions

  Expanding natural instructions

  Language:Python95821161189

• google-research-datasets/dstc8-schema-guided-dialogue

  The Schema-Guided Dialogue Dataset

  Language:Python5493850124

• reasoning-machines/pal

  PaL: Program-Aided Language Models (ICML 2023)

  Language:Python47491459

• princeton-nlp/LESS

  [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning

  Language:Jupyter Notebook37153532

• google-deepmind/synjax

  Language:Python24013214

• manyoso/haltt4llm

  This project is an attempt to create a common metric to test LLM's for progress in eliminating hallucinations which is the most serious current problem in widespread adoption of LLM's for many real purposes.

  Language:Python2203423

• jax-ml/oryx

  Oryx is a library for probabilistic programming and deep learning built on top of Jax.

  Language:Python219101910

• TransformerLensOrg/CircuitsVis

  Mechanistic Interpretability Visualizations using React

  Language:Jupyter Notebook19722631

• ArthurConmy/Automatic-Circuit-Discovery

  Language:Jupyter Notebook18701736

• OSU-NLP-Group/GrokkedTransformer

  Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'

  Language:Python1605512

• google-research-datasets/presto

  A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs

  113816

• seonghyeonye/TAPP

  [AAAI 2024] Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following

  Language:Python79642

• edenbiran/RippleEdits

  Evaluating the Ripple Effects of Knowledge Editing in Language Models

  Language:Python50574

• Nix07/finetuning

  This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking".

  Language:Jupyter Notebook17102

• edenbiran/HoppingTooLate

  Exploring the Limitations of Large Language Models on Multi-Hop Queries

  Language:Python121