cloneofsimo / min-max-gptLinks
Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
☆132Updated last year
Alternatives and similar repositories for min-max-gpt
Users that are interested in min-max-gpt are comparing it to the libraries listed below
Sorting:
- ☆89Updated last year
- supporting pytorch FSDP for optimizers☆84Updated 9 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆164Updated 3 months ago
- WIP☆93Updated last year
- Implementation of the Llama architecture with RLHF + Q-learning☆168Updated 8 months ago
- ☆53Updated last year
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆85Updated last year
- ☆82Updated last year
- Focused on fast experimentation and simplicity☆75Updated 9 months ago
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆56Updated 6 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆128Updated last year
- Automatically take good care of your preemptible TPUs☆36Updated 2 years ago
- A MAD laboratory to improve AI architecture designs 🧪☆129Updated 9 months ago
- Collection of autoregressive model implementation☆86Updated 5 months ago
- A set of Python scripts that makes your experience on TPU better☆54Updated 2 weeks ago
- JAX implementation of the Llama 2 model☆218Updated last year
- Understand and test language model architectures on synthetic tasks.☆229Updated last week
- Language models scale reliably with over-training and on downstream tasks☆100Updated last year
- ☆34Updated last year
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆193Updated last year
- nanoGPT-like codebase for LLM training☆107Updated 4 months ago
- Minimal but scalable implementation of large language models in JAX☆35Updated last month
- σ-GPT: A New Approach to Autoregressive Models☆68Updated last year
- Experiment of using Tangent to autodiff triton☆81Updated last year
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆130Updated 10 months ago
- Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*☆87Updated last year
- An implementation of the Llama architecture, to instruct and delight☆21Updated 4 months ago
- ☆53Updated last year
- Normalized Transformer (nGPT)☆191Updated 10 months ago