Ashone3

Ashone3's Stars

• google-research/nasbench

  NASBench: A Neural Architecture Search Dataset and Benchmark

  Language:Python687128

• mit-han-lab/hardware-aware-transformers

  [ACL'20] HAT: Hardware-Aware Transformers for Efficient Natural Language Processing

  Language:Python33153

• quark0/darts

  Differentiable architecture search for convolutional and recurrent networks

  Language:Python3.9k844

• automl/nas-bench-x11

  Language:Python194

• EleutherAI/lm-evaluation-harness

  A framework for few-shot evaluation of language models.

  Language:Python7.3k2k

• uukuguy/multi_loras

  Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answer based on user queries.

  Language:Python14710

• jha-lab/txf_design-space

  [JAIR'23] FlexiBERT tool for Transformer design space exploration.

  Language:Python81

• nikhilbarhate99/PPO-PyTorch

  Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch

  Language:Python1.8k353

• karpathy/nanoGPT

  The simplest, fastest repository for training/finetuning medium-sized GPTs.

  Language:Python38k6.1k

• LeeSinLiang/microGPT

  Implementation of GPT from scratch. Design to be lightweight and easy to modify.

  Language:Python4712

• predibase/lorax

  Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

  Language:Python2.3k149

• PlayVoice/lora-svc

  singing voice change based on whisper, and lora for singing voice clone

  Language:Python63278

• SamsungLabs/zero-cost-nas

  Zero-Cost Proxies for Lightweight NAS

  Language:Jupyter Notebook14320

• ssundaram21/dreamsim

  DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data (NeurIPS 2023 Spotlight) / / / / When Does Perceptual Alignment Benefit Vision Representations? (NeurIPS 2024)

  Language:Python42322

• Meituan-AutoML/MobileVLM

  Strong and Open Vision Language Assistant for Mobile Devices

  Language:Python1.1k69

• maszhongming/Multi-LoRA-Composition

  Repository for the Paper "Multi-LoRA Composition for Image Generation"

  Language:Python45247

• rattlesnakey/CoFiTune

  The code repository of CoFiTune framework

  Language:Python4

• facebookresearch/MobileLLM

  MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

  Language:Python1.2k67

• mathllm/MathCoder-o1

  4

• vllm-project/vllm

  A high-throughput and memory-efficient inference and serving engine for LLMs

  Language:Python32.3k4.9k

• mathllm/MathCoder2

  Language:Python535

• guoyww/AnimateDiff

  Official implementation of AnimateDiff.

  Language:Python10.8k877

• haotian-liu/LLaVA

  [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

  Language:Python20.8k2.3k

• opendatalab/MinerU

  A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

  Language:Python21.7k1.6k

• GATECH-EIC/HW-NAS-Bench

  [ICLR 2021] HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark

  Language:Python10516

• huggingface/alignment-handbook

  Robust recipes to align language models with human and AI preferences

  Language:Python4.8k418

• automl/nasbench301

  Language:Python7622

• carpedm20/ENAS-pytorch

  PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"

  Language:Python2.7k492

• mit-han-lab/proxylessnas

  [ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

  Language:C++1.4k285

• d-li14/mobilenetv2.pytorch

  72.8% MobileNetV2 1.0 model on ImageNet and a spectrum of pre-trained MobileNetV2 models

  Language:Python683189