kotoba-tech / kotomambaLinks
Mamba training library developed by kotoba technologies
☆71Updated last year
Alternatives and similar repositories for kotomamba
Users that are interested in kotomamba are comparing it to the libraries listed below
Sorting:
- Checkpointable dataset utilities for foundation model training☆32Updated last year
- Griffin MQA + Hawk Linear RNN Hybrid☆89Updated last year
- CycleQD is a framework for parameter space model merging.☆44Updated 7 months ago
- Example of using Epochraft to train HuggingFace transformers models with PyTorch FSDP☆11Updated last year
- Support Continual pre-training & Instruction Tuning forked from llama-recipes☆33Updated last year
- ☆15Updated last year
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆98Updated 11 months ago
- ☆61Updated last year
- ☆41Updated last year
- Fast, Modern, and Low Precision PyTorch Optimizers☆109Updated 2 weeks ago
- 0️⃣1️⃣🤗 BitNet-Transformers: Huggingface Transformers Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" i…☆307Updated last year
- Japanese LLaMa experiment☆55Updated 9 months ago
- Ongoing Research Project for continaual pre-training LLM(dense mode)☆42Updated 6 months ago
- Randomized Positional Encodings Boost Length Generalization of Transformers☆82Updated last year
- Token Omission Via Attention☆128Updated 11 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆38Updated 3 months ago
- A toolkit for scaling law research ⚖☆51Updated 7 months ago
- Implementation of Infini-Transformer in Pytorch☆111Updated 8 months ago
- Official implementation of "TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models"☆114Updated 7 months ago
- Ongoing research training Mixture of Expert models.☆20Updated last year
- Project of llm evaluation to Japanese tasks☆89Updated this week
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆128Updated last year
- some common Huggingface transformers in maximal update parametrization (µP)☆82Updated 3 years ago
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆229Updated last year
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆121Updated 11 months ago
- ☆19Updated last year
- ☆82Updated last year
- Recurrent Memory Transformer☆150Updated 2 years ago
- Code for pre-training BabyLM baseline models.☆16Updated 2 years ago
- LEIA: Facilitating Cross-Lingual Knowledge Transfer in Language Models with Entity-based Data Augmentation☆22Updated last year