Giters
Pumpkin (Neko9810)

Neko9810

Geek Repo

4

followers

41

following

669

stars

Github PK Tool:Github PK Tool

Pumpkin's starred repositories

cvxopt

CVXOPT -- Python Software for Convex Optimization

Language:CLicense:NOASSERTIONStargazers:968Issues:0Issues:0

cvxpy

A Python-embedded modeling language for convex optimization problems.

Language:C++License:Apache-2.0Stargazers:5231Issues:0Issues:0

zhao

【编程随想】整理的《太子党关系网络》，专门揭露赵国的权贵

Language:PythonLicense:GPL-3.0Stargazers:13428Issues:0Issues:0

HowToCook

程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).

Language:DockerfileLicense:UnlicenseStargazers:64333Issues:0Issues:0

JetMoE

Reaching LLaMA2 Performance with 0.1M Dollars

Language:PythonLicense:Apache-2.0Stargazers:947Issues:0Issues:0

SMDL-Attribution

[ICLR 2024 Oral] Less is More: Fewer Interpretable Region via Submodular Subset Selection

Language:Jupyter NotebookStargazers:63Issues:0Issues:0

easy-to-hard

Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision

Language:PythonLicense:BSD-3-ClauseStargazers:68Issues:0Issues:0

llm-sp

Papers and resources related to the security and privacy of LLMs 🤖

Language:PythonLicense:Apache-2.0Stargazers:319Issues:0Issues:0

pal

PAL: Proxy-Guided Black-Box Attack on Large Language Models

Language:PythonLicense:MITStargazers:38Issues:0Issues:0

OPERA

[CVPR 2024 Highlight] OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation

Language:PythonLicense:MITStargazers:213Issues:0Issues:0

minGPT

A minimal PyTorch Lightning OpenAI GPT w DeepSpeed Training!

Language:PythonStargazers:111Issues:0Issues:0

rlhf-poisoning

Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"

Language:PythonLicense:Apache-2.0Stargazers:36Issues:0Issues:0

mergekit

Tools for merging pretrained large language models.

Language:PythonLicense:LGPL-3.0Stargazers:4104Issues:0Issues:0

EasyContext

Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

Language:PythonLicense:Apache-2.0Stargazers:541Issues:0Issues:0

h2ogpt

Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://codellama.h2o.ai/

Language:PythonLicense:Apache-2.0Stargazers:11008Issues:0Issues:0

Monkey

【CVPR 2024 Highlight】Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models

Language:PythonLicense:MITStargazers:1571Issues:0Issues:0

hh-rlhf

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

License:MITStargazers:1506Issues:0Issues:0

Expert_Sparsity

[ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models

Language:PythonLicense:MITStargazers:58Issues:0Issues:0

safe-rlhf

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Language:PythonLicense:Apache-2.0Stargazers:1249Issues:0Issues:0

hydra

Hydra is a framework for elegantly configuring complex applications

Language:PythonLicense:MITStargazers:8416Issues:0Issues:0

HarmBench

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Language:Jupyter NotebookLicense:MITStargazers:216Issues:0Issues:0

UPD

[arXiv2024] Unsolvable Problem Detection: Evaluating Trustworthiness of Vision Language Models

Language:PythonLicense:Apache-2.0Stargazers:57Issues:0Issues:0

OpenMoE

A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

Language:PythonStargazers:1303Issues:0Issues:0

awesome-mixture-of-experts

A collection of AWESOME things about mixture-of-experts

Stargazers:842Issues:0Issues:0

optuna

A hyperparameter optimization framework

Language:PythonLicense:NOASSERTIONStargazers:10201Issues:0Issues:0

evotorch

Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.

Language:PythonLicense:Apache-2.0Stargazers:990Issues:0Issues:0

LEAP

A general purpose Library for Evolutionary Algorithms in Python.

Language:Jupyter NotebookLicense:AFL-3.0Stargazers:81Issues:0Issues:0

Awesome-Model-Merging

:couple: A curated list of Model Merging methods.

Stargazers:52Issues:0Issues:0

omnisafe

OmniSafe is an infrastructural framework for accelerating SafeRL research.

Language:PythonLicense:Apache-2.0Stargazers:882Issues:0Issues:0

one-person-businesses-methodology-v2.0

《一人企业方法论》第二版，也适合做其他副业（比如自媒体、电商、数字商品）的非技术人群。

Language:PHPLicense:NOASSERTIONStargazers:2539Issues:0Issues:0