Pinned Repositories
based
Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"
data-centric-ai
Resources for Data Centric AI
deepdive
DeepDive
hgcn
Hyperbolic Graph Convolutional Networks in PyTorch.
hyena-dna
Official implementation for HyenaDNA, a long-range genomic foundation model built with Hyena
m2
Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"
meerkat
Explore and understand your training and validation data.
minions
Big & Small LLMs working together
safari
Convolutions for Sequence Modeling
ThunderKittens
Tile primitives for speedy kernels
HazyResearch's Repositories
HazyResearch/ThunderKittens
Tile primitives for speedy kernels
HazyResearch/minions
Big & Small LLMs working together
HazyResearch/data-centric-ai
Resources for Data Centric AI
HazyResearch/safari
Convolutions for Sequence Modeling
HazyResearch/meerkat
Explore and understand your training and validation data.
HazyResearch/hyena-dna
Official implementation for HyenaDNA, a long-range genomic foundation model built with Hyena
HazyResearch/hgcn
Hyperbolic Graph Convolutional Networks in PyTorch.
HazyResearch/aisys-building-blocks
Building blocks for foundation models.
HazyResearch/m2
Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"
HazyResearch/evaporate
This repo contains data and code for the paper "Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes"
HazyResearch/manifest
Prompt programming with FMs.
HazyResearch/legalbench
An open science effort to benchmark legal reasoning in foundation models
HazyResearch/flash-fft-conv
FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores
HazyResearch/lolcats
Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"
HazyResearch/based
Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"
HazyResearch/zoology
Understand and test language model architectures on synthetic tasks.
HazyResearch/hippo-code
HazyResearch/eclair-agents
Automating enterprise workflows with multimodal agents
HazyResearch/train-tk
train with kittens!
HazyResearch/prefix-linear-attention
HazyResearch/skill-it
Skill-It! A Data-Driven Skills Framework for Understanding and Training Language Models
HazyResearch/wonderbread
WONDERBREAD benchmark + dataset for BPM tasks
HazyResearch/aioli
Aioli: A unified optimization framework for language model data mixing
HazyResearch/based-evaluation-harness
A framework for few-shot evaluation of language models.
HazyResearch/olive-evaluation-harness
A framework for few-shot evaluation of language models.
HazyResearch/smoothie
HazyResearch/precision-ls
HazyResearch/axolive
Go ahead and axolotl questions
HazyResearch/olive-recipes
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
HazyResearch/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs