Highlights
- Pro
Block or Report
Block or report ranonrkm
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseStars
Language
Sort by: Recently starred
Disaggregated serving system for Large Language Models (LLMs).
Long Range Arena for Benchmarking Efficient Transformers
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
RAGs: Simple implementations of Retrieval Augmented Generation (RAG) Systems
Universal and Transferable Attacks on Aligned Language Models
LlamaIndex is a data framework for your LLM applications
GGNN: State of the Art Graph-based GPU Nearest Neighbor Search
CUDA implementation of Hierarchical Navigable Small World Graph algorithm
KDEformer can approximate the attention in sub-quadratic time with provable spectral norm bounds.
Weighted MinHash implementation on CUDA (multi-gpu).
PyTorch Language Model for 1-Billion Word (LM1B / GBW) Dataset
A project for clustering text streams using locality-sensitive hashing (LSH) in Python
Try to implement pre-training and fine-tuning GPT-2 model for research and education purpose.
[ACL 2022] LinkBERT: A Knowledgeable Language Model 😎 Pretrained with Document Links
Implementaion of our EMNLP 2023 submission "Nearest Neighbor Machine Translation is Meta-Optimizer on Output Projection Layer"
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Landmark Attention: Random-Access Infinite Context Length for Transformers
🧑🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gan…
Efficient GPU kernels for block-sparse matrix multiplication and convolution
A plugin for [Obsidian](https://obsidian.md) which allows syntax highlighting for code blocks in the editor.