EleutherAI / nanoGPT-mupLinks
The simplest, fastest repository for training/finetuning medium-sized GPTs.
โ149Updated last month
Alternatives and similar repositories for nanoGPT-mup
Users that are interested in nanoGPT-mup are comparing it to the libraries listed below
Sorting:
- Understand and test language model architectures on synthetic tasks.โ221Updated 3 weeks ago
- A MAD laboratory to improve AI architecture designs ๐งชโ123Updated 7 months ago
- supporting pytorch FSDP for optimizersโ84Updated 7 months ago
- nanoGPT-like codebase for LLM trainingโ102Updated 2 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"โ238Updated last month
- โ83Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT trainingโ130Updated last year
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)โ190Updated last year
- โ53Updated last year
- Normalized Transformer (nGPT)โ185Updated 8 months ago
- A set of Python scripts that makes your experience on TPU betterโ54Updated last year
- 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"โ77Updated 9 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmindโ127Updated 11 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clustersโ127Updated 8 months ago
- Custom triton kernels for training Karpathy's nanoGPT.โ19Updated 9 months ago
- โ83Updated 11 months ago
- Some preliminary explorations of Mamba's context scaling.โ216Updated last year
- some common Huggingface transformers in maximal update parametrization (ยตP)โ82Updated 3 years ago
- Mixture of A Million Expertsโ46Updated last year
- Implementation of ๐ฅฅ Coconut, Chain of Continuous Thought, in Pytorchโ178Updated last month
- โ81Updated last year
- Accelerated First Order Parallel Associative Scanโ184Updated 11 months ago
- Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for trโฆโ64Updated 9 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.โ82Updated 2 weeks ago
- โ166Updated 2 years ago
- โ347Updated this week
- โ134Updated 4 months ago
- โ100Updated last week
- โ53Updated 10 months ago