athms / mad-labLinks
A MAD laboratory to improve AI architecture designs ๐งช
โ116Updated 5 months ago
Alternatives and similar repositories for mad-lab
Users that are interested in mad-lab are comparing it to the libraries listed below
Sorting:
- Understand and test language model architectures on synthetic tasks.โ197Updated 3 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.โ128Updated 3 weeks ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"โ234Updated 3 months ago
- โ52Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clustersโ126Updated 6 months ago
- Some preliminary explorations of Mamba's context scaling.โ214Updated last year
- seqax = sequence modeling + JAXโ155Updated 2 months ago
- Normalized Transformer (nGPT)โ182Updated 6 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"โ73Updated 7 months ago
- Accelerated First Order Parallel Associative Scanโ181Updated 9 months ago
- โ78Updated 11 months ago
- some common Huggingface transformers in maximal update parametrization (ยตP)โ80Updated 3 years ago
- nanoGPT-like codebase for LLM trainingโ94Updated 3 weeks ago
- supporting pytorch FSDP for optimizersโ79Updated 6 months ago
- โ53Updated last year
- Language models scale reliably with over-training and on downstream tasksโ97Updated last year
- Stick-breaking attentionโ56Updated 2 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"โ237Updated 4 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.โ62Updated 4 months ago
- โ182Updated this week
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)โ190Updated last year
- EvaByte: Efficient Byte-level Language Models at Scaleโ101Updated last month
- โ79Updated 9 months ago
- โ144Updated 2 years ago
- โ37Updated last year
- Token Omission Via Attentionโ126Updated 7 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmindโ126Updated 9 months ago
- โ81Updated last year
- โ179Updated last year
- JAX bindings for Flash Attention v2โ89Updated 10 months ago