AlxSp / t-jepaLinks
☆12Updated last year
Alternatives and similar repositories for t-jepa
Users that are interested in t-jepa are comparing it to the libraries listed below
Sorting:
- Training Models Daily☆17Updated 2 years ago
- GoldFinch and other hybrid transformer components☆12Updated last month
- [WIP] Transformer to embed Danbooru labelsets☆13Updated last year
- ☆34Updated last year
- Cerule - A Tiny Mighty Vision Model☆68Updated 2 months ago
- Collection of autoregressive model implementation☆85Updated this week
- ☆63Updated last year
- Simplex Random Feature attention, in PyTorch☆75Updated 2 years ago
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated 8 months ago
- ☆50Updated last year
- ☆40Updated last year
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆103Updated last year
- A synthetic story narration dataset to study small audio LMs.☆31Updated last year
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆109Updated 10 months ago
- Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for tr…☆66Updated last month
- Latent Large Language Models☆19Updated last year
- LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence☆61Updated 3 years ago
- ☆27Updated last year
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆18Updated 5 months ago
- An open source replication of the stawberry method that leverages Monte Carlo Search with PPO and or DPO☆29Updated last month
- ☆39Updated last year
- recipe for training fully-featured self supervised image jepa models☆12Updated 7 months ago
- Experiments for efforts to train a new and improved t5☆76Updated last year
- Lightweight package that tracks and summarizes code changes using LLMs (Large Language Models)☆34Updated 10 months ago
- ☆137Updated last year
- ☆22Updated last year
- JAX Scalify: end-to-end scaled arithmetics☆17Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated 2 years ago
- ☆24Updated last year
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆32Updated 3 months ago