PgLoLo / optiactsLinks
☆20Updated last year
Alternatives and similar repositories for optiacts
Users that are interested in optiacts are comparing it to the libraries listed below
Sorting:
- Skoltech NLA 2024 course.☆35Updated 11 months ago
- Official implementation of the paper "Linear Transformers with Learnable Kernel Functions are Better In-Context Models"☆165Updated 10 months ago
- A neural network training framework within a task-based parallel programming paradigm☆54Updated last week
- ☆70Updated last year
- ☆22Updated 2 years ago
- Effective LLM Alignment Toolkit☆148Updated 4 months ago
- Modified Arena-Hard-Auto LLM evaluation toolkit with an emphasis on Russian language☆45Updated 7 months ago
- Skoltech 2023 NLA course☆31Updated last year
- Code for the paper "PALBERT: Teaching ALBERT to Ponder", NeurIPS 2022 Spotlight☆37Updated 2 years ago
- ☆31Updated last year
- Framework for processing and filtering datasets☆28Updated last year
- Official implementation of the paper "You Do Not Fully Utilize Transformer's Representation Capacity"☆31Updated 5 months ago
- ☆18Updated 2 weeks ago
- Compression schema for gradients of activations in backward pass☆44Updated 2 years ago
- This is the official implementation of "ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models"☆48Updated 5 months ago
- GULAG: GUessing LAnGuages with neural networks☆13Updated 3 years ago
- The official implementation of "Smoothie: Smoothing Diffusion on Token Embeddings for Text Generation"☆23Updated this week
- ☆20Updated last year
- Efficient DL/ML Models Seminars☆32Updated 10 months ago
- Augmentex — a library for augmenting texts with errors☆68Updated last year
- MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating fundament…☆62Updated last year
- ☆18Updated 7 months ago
- Development of a prototype engine for searching for goods on the tender procurement portal☆27Updated 3 years ago
- A FlashAttention implementation for JAX with support for efficient document mask computation and context parallelism.☆149Updated last week
- RuCLIP tiny (Russian Contrastive Language–Image Pretraining) is a neural network trained to work with different pairs (images, texts).☆35Updated 3 years ago
- Single-line inference of SOTA deep learning models☆29Updated 2 years ago
- NLA 2018 Skoltech course☆55Updated 6 years ago
- The solution and code for NTO AI Olympics 2022.☆19Updated 3 years ago
- Deep Generative Models course, 2021☆22Updated 3 years ago
- ☆19Updated 11 months ago