apple / ml-dataset-decompositionLinks
Official repo of dataset-decomposition paper [NeurIPS 2024]
☆19Updated 7 months ago
Alternatives and similar repositories for ml-dataset-decomposition
Users that are interested in ml-dataset-decomposition are comparing it to the libraries listed below
Sorting:
- Common tools for data processing☆18Updated 2 weeks ago
- A repository for research on medium sized language models.☆78Updated last year
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆60Updated last year
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆44Updated last year
- GoldFinch and other hybrid transformer components☆45Updated last year
- ☆85Updated last year
- Official code repo for paper "Great Memory, Shallow Reasoning: Limits of kNN-LMs"☆23Updated 4 months ago
- Language models scale reliably with over-training and on downstream tasks☆98Updated last year
- [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers☆70Updated 2 months ago
- ☆103Updated 11 months ago
- Codebase for Instruction Following without Instruction Tuning☆35Updated 11 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆33Updated last week
- ☆48Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆82Updated 10 months ago
- ☆38Updated last year
- ☆53Updated 10 months ago
- Long Context Extension and Generalization in LLMs☆58Updated 11 months ago
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Updated last year
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆70Updated last year
- Code for Zero-Shot Tokenizer Transfer☆135Updated 7 months ago
- The official code repo and data hub of top_nsigma sampling strategy for LLMs.☆26Updated 6 months ago
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆33Updated last year
- The official implementation for Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free☆48Updated 3 months ago
- Official code release for "SuperBPE: Space Travel for Language Models"☆64Updated last month
- DPO, but faster 🚀☆44Updated 8 months ago
- ☆19Updated 2 years ago
- [NAACL 2025] A Closer Look into Mixture-of-Experts in Large Language Models☆54Updated 6 months ago
- ☆32Updated last year
- PyTorch implementation of StableMask (ICML'24)☆14Updated last year
- ☆49Updated last year