nikg4/relbench
RelBench: Relational Deep Learning Benchmark
Repositories
nikg4/relational-transformer
Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data
nikg4/adk-python
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
nikg4/genai-on-google-cloud
GenAI on Google Cloud: Enterprise Generative AI Systems and Agents
nikg4/icu4x
Solving i18n for client-side and resource-constrained environments.
nikg4/tiktoken-rs
Ready-made tokenizer library for working with GPT and tiktoken
nikg4/tokenizers
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
nikg4/text-splitter
Split text into semantic chunks, up to a desired chunk size. Supports calculating length by characters and tokens, and is callable from Rust and Python.
nikg4/RustGPT
An transformer based LLM. Written completely in Rust
nikg4/pytorch-memory-efficient-attention-pytorch
Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"
nikg4/kiamol
Learn Kubernetes in a Month of Lunches
nikg4/attention-gym
Helpful tools and examples for working with flex-attention
nikg4/LLaVA-MORE
LLaVA-MORE: Enhancing Visual Instruction Tuning with LLaMA 3.1
nikg4/aminrezae-memory-efficient-attention
Memory Efficient Attention (O(sqrt(n)) for Jax and PyTorch
nikg4/context-parallelism
Context Parallelism, support Blockwise Attention, Ring Attention and Tree Attention.
nikg4/oyEasyContext
modified on origin repo
nikg4/ringattention
Transformers with Arbitrarily Large Context
nikg4/EasyContext
Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.
nikg4/cambrian
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
nikg4/LightSeq
Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers
nikg4/smol-vision
Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜
nikg4/ring-flash-attention
Ring attention implementation with flash attention
nikg4/oumi-poseidon
nikg4/ALCF_Hands_on_HPC_Workshop
The ALCF hosts a regular simulation, data, and learning workshop to help users scale their applications. This repository contains the examples used in the workshop.
nikg4/Megatron-DeepSpeed
Ongoing research training transformer language models at scale, including: BERT & GPT-2
nikg4/tree_attention
Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
nikg4/mlx-examples
Examples in the MLX framework
nikg4/VILA
VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)
nikg4/RustOrBust
My Rust deep dive down the rabbit-hole !
nikg4/ProLong
Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"