apple / ml-sigma-reparamLinks
☆303Updated last year
Alternatives and similar repositories for ml-sigma-reparam
Users that are interested in ml-sigma-reparam are comparing it to the libraries listed below
Sorting:
- For optimization algorithm research and development.☆521Updated this week
- WIP☆93Updated 10 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆127Updated last year
- Annotated version of the Mamba paper☆485Updated last year
- ☆78Updated 11 months ago
- JAX implementation of the Llama 2 model☆218Updated last year
- Efficient optimizers☆212Updated last week
- ☆166Updated last year
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆214Updated 10 months ago
- ☆270Updated 11 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆134Updated this week
- The AdEMAMix Optimizer: Better, Faster, Older.☆183Updated 9 months ago
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆251Updated 3 months ago
- supporting pytorch FSDP for optimizers☆82Updated 6 months ago
- Implementation of Diffusion Transformer (DiT) in JAX☆278Updated last year
- seqax = sequence modeling + JAX☆159Updated last week
- Fast bare-bones BPE for modern tokenizer training☆159Updated 2 months ago
- Scalable and Performant Data Loading☆277Updated this week
- Getting crystal-like representations with harmonic loss☆189Updated 2 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆235Updated 2 weeks ago
- σ-GPT: A New Approach to Autoregressive Models☆65Updated 10 months ago
- ☆53Updated last year
- A simple implimentation of Bayesian Flow Networks (BFN)☆240Updated last year
- Understand and test language model architectures on synthetic tasks.☆217Updated 2 weeks ago
- A repository for log-time feedforward networks☆222Updated last year
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆122Updated 10 months ago
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆381Updated last year
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆230Updated 9 months ago
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆284Updated 2 weeks ago
- Implementation of the Llama architecture with RLHF + Q-learning☆165Updated 4 months ago