jdeschena / sdttLinks
[ICLR 2025] SDTT: a simple and effective distillation method for discrete diffusion models
☆28Updated 2 months ago
Alternatives and similar repositories for sdtt
Users that are interested in sdtt are comparing it to the libraries listed below
Sorting:
- CycleQD is a framework for parameter space model merging.☆40Updated 4 months ago
- Checkpointable dataset utilities for foundation model training☆32Updated last year
- Official implementation of "TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models"☆106Updated 4 months ago
- Mamba training library developed by kotoba technologies☆71Updated last year
- Memory Mosaics are networks of associative memories working in concert to achieve a prediction task.☆44Updated 4 months ago
- An AI benchmark for creative, human-like problem solving using Sudoku variants☆70Updated last month
- ☆22Updated last year
- Remasking Discrete Diffusion Models with Inference-Time Scaling☆26Updated 3 months ago
- Code for Discovering Preference Optimization Algorithms with and for Large Language Models☆63Updated last year
- The official repository of ALE-Bench☆78Updated last week
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- Plug in & Play Pytorch Implementation of the paper: "Evolutionary Optimization of Model Merging Recipes" by Sakana AI☆30Updated 7 months ago
- This repo is based on https://github.com/jiaweizzhao/GaLore☆28Updated 9 months ago
- ☆32Updated last year
- ☆14Updated last year
- ☆33Updated 3 months ago
- ☆79Updated 10 months ago
- Example of using Epochraft to train HuggingFace transformers models with PyTorch FSDP☆11Updated last year
- RS-IMLE☆40Updated 6 months ago
- One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation☆40Updated 8 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆38Updated 2 weeks ago
- Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"☆29Updated 7 months ago
- ☆16Updated 9 months ago
- Using FlexAttention to compute attention with different masking patterns☆44Updated 9 months ago
- [NeurIPS 2022] Your Transformer May Not be as Powerful as You Expect (official implementation)☆34Updated last year
- ☆17Updated 7 months ago
- [Oral; Neurips OPT2024 ] μLO: Compute-Efficient Meta-Generalization of Learned Optimizers☆13Updated 3 months ago
- Codes for the paper "A mathematical perspective on Transformers".☆37Updated 11 months ago
- One-D-Piece: Image Tokenizer Meets Quality-Controllable Compression☆55Updated this week
- Efficient Scaling laws and collaborative pretraining.☆16Updated 4 months ago