cofe-ai / Mu-scalingLinks
Research without Re-search: Maximal Update Parametrization Yields Accurate Loss Prediction across Scales
☆32Updated last year
Alternatives and similar repositories for Mu-scaling
Users that are interested in Mu-scaling are comparing it to the libraries listed below
Sorting:
- [ICLR 2024] CLEX: Continuous Length Extrapolation for Large Language Models☆78Updated last year
- ☆101Updated 8 months ago
- Towards Systematic Measurement for Long Text Quality☆35Updated 9 months ago
- [ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.☆63Updated 7 months ago
- Official completion of “Training on the Benchmark Is Not All You Need”.☆34Updated 5 months ago
- Official implementation of the paper "From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large L…☆50Updated last year
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆57Updated last year
- [ICLR'24 spotlight] Tool-Augmented Reward Modeling☆50Updated 2 weeks ago
- 🍼 Official implementation of Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts☆39Updated 8 months ago
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"☆73Updated last month
- ☆48Updated last year
- The code and data for the paper JiuZhang3.0☆46Updated last year
- Revisiting Mid-training in the Era of RL Scaling☆56Updated 2 months ago
- A prototype repo for hybrid training of pipeline parallel and distributed data parallel with comments on core code snippets. Feel free to…☆55Updated last year
- [ACL 2025, Main Conference] Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process☆28Updated 10 months ago
- [ICLR 2025] 🧬 RegMix: Data Mixture as Regression for Language Model Pre-training (Spotlight)☆146Updated 4 months ago
- Source code of "Reasons to Reject? Aligning Language Models with Judgments"☆58Updated last year
- An Experiment on Dynamic NTK Scaling RoPE☆64Updated last year
- Implementations of online merging optimizers proposed by Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment☆75Updated last year
- On Memorization of Large Language Models in Logical Reasoning☆67Updated 2 months ago
- code for Scaling Laws of RoPE-based Extrapolation☆73Updated last year
- We aim to provide the best references to search, select, and synthesize high-quality and large-quantity data for post-training your LLMs.☆57Updated 8 months ago
- ☆35Updated last year
- ☆30Updated 5 months ago
- The official implementation for Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free☆44Updated last month
- Code for paper "Patch-Level Training for Large Language Models"☆85Updated 7 months ago
- ☆14Updated 11 months ago
- Code for preprint "Metadata Conditioning Accelerates Language Model Pre-training (MeCo)"☆39Updated last month
- [ICML'2024] Can AI Assistants Know What They Don't Know?☆81Updated last year
- [NeurIPS-2024] 📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies https://arxiv.org/abs/2407.13623☆85Updated 8 months ago