HazyResearch / zoologyLinks
Understand and test language model architectures on synthetic tasks.
โ195Updated 2 months ago
Alternatives and similar repositories for zoology
Users that are interested in zoology are comparing it to the libraries listed below
Sorting:
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"โ233Updated 3 months ago
- A MAD laboratory to improve AI architecture designs ๐งชโ116Updated 5 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.โ126Updated 3 weeks ago
- Some preliminary explorations of Mamba's context scaling.โ212Updated last year
- supporting pytorch FSDP for optimizersโ79Updated 5 months ago
- Language models scale reliably with over-training and on downstream tasksโ97Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clustersโ126Updated 5 months ago
- โ78Updated 10 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"โ236Updated 4 months ago
- โ144Updated last year
- nanoGPT-like codebase for LLM trainingโ94Updated 2 weeks ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmindโ124Updated 9 months ago
- Normalized Transformer (nGPT)โ181Updated 6 months ago
- โ52Updated last year
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)โ189Updated last year
- โ190Updated this week
- โ159Updated this week
- Token Omission Via Attentionโ126Updated 7 months ago
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.โ67Updated 9 months ago
- seqax = sequence modeling + JAXโ155Updated last month
- Accelerated First Order Parallel Associative Scanโ180Updated 9 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.โ62Updated 4 months ago
- โ166Updated last year
- โ53Updated last year
- โ81Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT trainingโ127Updated last year
- Mixture of A Million Expertsโ45Updated 10 months ago
- some common Huggingface transformers in maximal update parametrization (ยตP)โ80Updated 3 years ago
- โ79Updated 9 months ago
- Triton-based implementation of Sparse Mixture of Experts.โ216Updated 6 months ago