HazyResearch / basedLinks
Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"
β238Updated 2 months ago
Alternatives and similar repositories for based
Users that are interested in based are comparing it to the libraries listed below
Sorting:
- Understand and test language model architectures on synthetic tasks.β221Updated 3 weeks ago
- A MAD laboratory to improve AI architecture designs π§ͺβ123Updated 7 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"β244Updated 6 months ago
- β147Updated 2 years ago
- Some preliminary explorations of Mamba's context scaling.β216Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clustersβ127Updated 8 months ago
- β192Updated last week
- β114Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.β149Updated last month
- Normalized Transformer (nGPT)β185Updated 8 months ago
- Multipack distributed sampler for fast padding-free training of LLMsβ199Updated 11 months ago
- β81Updated last year
- Triton-based implementation of Sparse Mixture of Experts.β230Updated 8 months ago
- Token Omission Via Attentionβ128Updated 9 months ago
- some common Huggingface transformers in maximal update parametrization (Β΅P)β82Updated 3 years ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performanceβ¦β151Updated 3 months ago
- Fast and memory-efficient exact attentionβ69Updated 5 months ago
- β53Updated last year
- β199Updated 8 months ago
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.β70Updated last year
- Griffin MQA + Hawk Linear RNN Hybridβ88Updated last year
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.β82Updated 2 weeks ago
- Accelerated First Order Parallel Associative Scanβ184Updated 11 months ago
- β127Updated last year
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top ofβ¦β138Updated 11 months ago
- Code for studying the super weight in LLMβ114Updated 8 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)β190Updated last year
- Implementation of π₯₯ Coconut, Chain of Continuous Thought, in Pytorchβ178Updated last month
- The evaluation framework for training-free sparse attention in LLMsβ86Updated last month
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS β¦β61Updated 9 months ago