SeunghyunSEO

SeunghyunSEO's Stars

• microsoft/generative-ai-for-beginners

  21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

  Language:Jupyter Notebook65.2k56012933.3k

• meta-llama/llama3

  The official Meta Llama 3 GitHub site

  Language:Python27.2k2262643.1k

• unslothai/unsloth

  Finetune Llama 3.2, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory

  Language:Python18.4k1291k1.3k

• openai/tiktoken

  tiktoken is a fast BPE tokeniser for use with OpenAI's models.

  Language:Python12.4k168240857

• plasma-umass/scalene

  Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals

  Language:Python12.2k91476399

• facebookresearch/DiT

  Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

  Language:Python6.4k4481570

• mosaicml/llm-foundry

  LLM training code for Databricks foundation models

  Language:Python4.1k48383530

• openai/transformer-debugger

  Language:Python4k2514238

• pytorch/torchtitan

  A native PyTorch Library for large model training

  Language:Python2.6k42178205

• AnswerDotAI/fsdp_qlora

  Training LLMs with QLoRA + FSDP

  Language:Jupyter Notebook1.4k2338188

• microsoft/mup

  maximal update parametrization (µP)

  Language:Jupyter Notebook1.4k296295

• databricks/megablocks

  Language:Python1.2k1661175

• cuda-mode/resource-stream

  CUDA related news and material links

  1.1k37267

• lilacai/lilac

  Curate better data for LLMs

  Language:Python9461329389

• mistralai/megablocks-public

  Language:Python8609055

• jzhang38/EasyContext

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

  Language:Python64784646

• alibaba/Megatron-LLaMA

  Best practice for training LLaMA models in Megatron-LM

  Language:Python62866351

• zhuzilin/ring-flash-attention

  Ring attention implementation with flash attention

  Language:Python588103546

• cloneofsimo/minRF

  Minimal implementation of scalable rectified flow transformers, based on SD3's approach

  Language:Jupyter Notebook4456934

• lucidrains/triton-transformer

  Implementation of a Transformer, but completely in Triton

  Language:Python24815915

• foundation-model-stack/fms-fsdp

  🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash attention v2.

  Language:Python193123432

• cloneofsimo/d3pm

  Minimal Implementation of a D3PM in pytorch

  Language:Jupyter Notebook1834815

• cloneofsimo/min-max-gpt

  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training

  Language:Python113425

• mgmalek/efficient_cross_entropy

  Language:Python77347

• qtli/GSM-Plus

  GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.

  Language:Python46134

• cloneofsimo/auto_llm_codebase_analysis

  Language:Python26201

• cloneofsimo/project_RF

  Language:Python24201

• likenneth/persona_drift

  Measuring and Controlling Persona Drift in Language Model Dialogs

  Language:Python12223

• cloneofsimo/reverse_eng_deepspeed_study

  DeepSpeed Study, focused on reverse engineering and enhancing documentation

  Language:Python5201

• mgmalek/ring-attention

  Language:Python4300