microsoft / mutransformersLinks
some common Huggingface transformers in maximal update parametrization (ยตP)
โ80Updated 3 years ago
Alternatives and similar repositories for mutransformers
Users that are interested in mutransformers are comparing it to the libraries listed below
Sorting:
- A MAD laboratory to improve AI architecture designs ๐งชโ120Updated 6 months ago
- Code repository for the c-BTM paperโ106Updated last year
- Exploring finetuning public checkpoints on filter 8K sequences on Pileโ115Updated 2 years ago
- โ74Updated last year
- Understand and test language model architectures on synthetic tasks.โ217Updated 2 weeks ago
- Language models scale reliably with over-training and on downstream tasksโ97Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"โ74Updated 7 months ago
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023โ136Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.โ134Updated this week
- โ78Updated 11 months ago
- Experiments for efforts to train a new and improved t5โ77Updated last year
- โ108Updated last year
- nanoGPT-like codebase for LLM trainingโ98Updated last month
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"โ235Updated 2 weeks ago
- Large scale 4D parallelism pre-training for ๐ค transformers in Mixture of Experts *(still work in progress)*โ82Updated last year
- Inference code for LLaMA models in JAXโ118Updated last year
- Official Repository of Pretraining Without Attention (BiGS), BiGS is the first model to achieve BERT-level transfer learning on the GLUE โฆโ113Updated last year
- โ38Updated last year
- Triton Implementation of HyperAttention Algorithmโ48Updated last year
- โ166Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT trainingโ127Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS โฆโ59Updated 8 months ago
- Multipack distributed sampler for fast padding-free training of LLMsโ191Updated 10 months ago
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.โ68Updated 10 months ago
- โ53Updated last year
- Randomized Positional Encodings Boost Length Generalization of Transformersโ81Updated last year
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.โ70Updated last week
- Experiments with generating opensource language model assistantsโ97Updated 2 years ago
- Simple and efficient pytorch-native transformer training and inference (batched)โ76Updated last year
- โ53Updated last year