athms / mad-labLinks
A MAD laboratory to improve AI architecture designs ๐งช
โ131Updated 10 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.โ233Updated last month
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"โ241Updated 4 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.โ168Updated 4 months ago
- โ53Updated last year
- nanoGPT-like codebase for LLM trainingโ109Updated 5 months ago
- Accelerated First Order Parallel Associative Scanโ189Updated last year
- Some preliminary explorations of Mamba's context scaling.โ216Updated last year
- Normalized Transformer (nGPT)โ192Updated 11 months ago
- seqax = sequence modeling + JAXโ168Updated 3 months ago
- some common Huggingface transformers in maximal update parametrization (ยตP)โ86Updated 3 years ago
- โ91Updated last year
- โ200Updated last week
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)โ193Updated last year
- A toolkit for scaling law research โโ52Updated 9 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"โ84Updated last year
- โ166Updated 2 years ago
- supporting pytorch FSDP for optimizersโ83Updated 10 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clustersโ130Updated 10 months ago
- โ53Updated last year
- Griffin MQA + Hawk Linear RNN Hybridโ89Updated last year
- Token Omission Via Attentionโ127Updated last year
- โ149Updated 2 years ago
- โ83Updated last year
- โ38Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT trainingโ132Updated last year
- Simple and efficient pytorch-native transformer training and inference (batched)โ78Updated last year
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"โ248Updated 8 months ago
- โ184Updated last year
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.โ260Updated last week
- โ81Updated last year