Code for ICML 25 paper "Metadata Conditioning Accelerates Language Model Pre-training (MeCo)"
☆51Jun 30, 2025Updated last year
Alternatives and similar repositories for MeCo
Users that are interested in MeCo are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆71Oct 16, 2024Updated last year
- ☆44Oct 13, 2023Updated 2 years ago
- Socratic-Zero is a fully autonomous framework that generates high-quality training data for mathematical reasoning☆38Oct 26, 2025Updated 8 months ago
- QRHead: Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking☆39Jan 20, 2026Updated 5 months ago
- In-Context Alignment: Chat with Vanilla Language Models Before Fine-Tuning☆34Aug 9, 2023Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Code for "Improving Translation Faithfulness of Large Language Models via Augmenting Instructions"☆12Aug 26, 2023Updated 2 years ago
- ☆248Oct 27, 2025Updated 8 months ago
- [Findings of EMNLP22] From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models☆19Mar 16, 2023Updated 3 years ago
- The official implementation of dLLM-Var☆35Nov 6, 2025Updated 8 months ago
- [ICML 2025] Predictive Data Selection: The Data That Predicts Is the Data That Teaches☆66Mar 4, 2025Updated last year
- Explanation Optimization☆13Oct 16, 2020Updated 5 years ago
- Official repo of dataset-decomposition paper [NeurIPS 2024]☆21Jan 8, 2025Updated last year
- This is the official repository of the paper Exploring Superior Function Calls via Reinforcement Learning.☆33Aug 11, 2025Updated 10 months ago
- Implementation of "Towards Understanding Mixture of Experts in Deep Learning", NeurIPS 2022☆10Jan 6, 2023Updated 3 years ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Provably (and non-vacuously) bounding test error of deep neural networks under distribution shift with unlabeled test data.☆10Feb 27, 2024Updated 2 years ago
- Implementation for the paper "Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning"☆11Jan 10, 2025Updated last year
- ☆24Jul 24, 2023Updated 2 years ago
- ☆15Feb 21, 2024Updated 2 years ago
- The SAIL-VL2 series model developed by the BytedanceDouyinContent Group☆80Sep 18, 2025Updated 9 months ago
- ☆11Apr 23, 2023Updated 3 years ago
- Code Roberta version of RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder☆10Mar 16, 2023Updated 3 years ago
- ☆125Jun 2, 2026Updated last month
- ☆13Nov 26, 2021Updated 4 years ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ☆18May 15, 2021Updated 5 years ago
- Open-source Human Feedback Library☆11Oct 25, 2023Updated 2 years ago
- ☆23Mar 31, 2023Updated 3 years ago
- Code for Evaluating Explanations for Reading Comprehension with Realistic Counterfactuals.☆17Apr 25, 2021Updated 5 years ago
- ☆19Jun 10, 2024Updated 2 years ago
- some mixture of experts architecture implementations☆27Mar 22, 2024Updated 2 years ago
- Code for our paper Resources and Evaluations for Multi-Distribution Dense Information Retrieval☆17Jan 16, 2024Updated 2 years ago
- Distributed pretraining of large language models (LLMs) on cloud TPU slices, with Jax and Equinox.☆26Sep 29, 2024Updated last year
- A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.☆232Jul 25, 2025Updated 11 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ☆48Jun 8, 2020Updated 6 years ago
- Federated Learning - PyTorch☆15Jun 27, 2021Updated 5 years ago
- The Code and Script of "David's Slingshot: A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis"☆34Jun 13, 2025Updated last year
- ☆16Dec 21, 2023Updated 2 years ago
- Contextual Position Encoding but with some custom CUDA Kernels https://arxiv.org/abs/2405.18719☆22Jun 5, 2024Updated 2 years ago
- Repo for WWW 2022 paper: Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval☆16Mar 1, 2022Updated 4 years ago
- GPT Demo with hybrid distributed training☆10Dec 1, 2022Updated 3 years ago