aitsc / GLMKDLinks
Are Intermediate Layers and Labels Really Necessary? A General Language Model Distillation Method ; GKD: A General Knowledge Distillation Framework for Large-scale Pre-trained Language Model
☆32Updated 2 years ago
Alternatives and similar repositories for GLMKD
Users that are interested in GLMKD are comparing it to the libraries listed below
Sorting:
- ☆106Updated 3 months ago
- [ACL 2024] Long-Context Language Modeling with Parallel Encodings☆165Updated last year
- [ICLR 2025] 🧬 RegMix: Data Mixture as Regression for Language Model Pre-training (Spotlight)☆173Updated 8 months ago
- [ICLR 2024] CLEX: Continuous Length Extrapolation for Large Language Models☆78Updated last year
- [ICML 2024] Selecting High-Quality Data for Training Language Models☆192Updated last year
- This PyTorch package implements MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation (NAACL 2022).☆112Updated 3 years ago
- [ACL'24] Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning☆180Updated 4 months ago
- ☆105Updated 2 years ago
- ☆54Updated last year
- An Experiment on Dynamic NTK Scaling RoPE☆64Updated last year
- Implementation of ICML 23 Paper: Specializing Smaller Language Models towards Multi-Step Reasoning.☆132Updated 2 years ago
- ☆140Updated last year
- Implementations of online merging optimizers proposed by Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment☆77Updated last year
- Repo for the EMNLP'24 Paper "Dual-Space Knowledge Distillation for Large Language Models". A general white-box KD framework for both same…☆60Updated 2 months ago
- Code for ACL2023 paper: Pre-Training to Learn in Context☆107Updated last year
- Retrieval as Attention☆82Updated 2 years ago
- ☆34Updated last year
- A prototype repo for hybrid training of pipeline parallel and distributed data parallel with comments on core code snippets. Feel free to…☆57Updated 2 years ago
- [ICLR'24 spotlight] Tool-Augmented Reward Modeling☆51Updated 4 months ago
- Codes for our paper "Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation" (EMNLP 2023 Findings)☆44Updated last year
- DSIR large-scale data selection framework for language model training☆263Updated last year
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆38Updated last year
- Code implementation of synthetic continued pretraining☆135Updated 9 months ago
- [NeurIPS 2023] Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective☆36Updated 2 years ago
- Repository for "Propagating Knowledge Updates to LMs Through Distillation" (NeurIPS 2023).☆26Updated last year
- ☆65Updated last year
- Lightweight tool to identify Data Contamination in LLMs evaluation☆52Updated last year
- [ICML'2024] Can AI Assistants Know What They Don't Know?☆83Updated last year
- ☆69Updated last year
- [ACL 2025, Main Conference, Oral] Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process☆30Updated last year