metadata
title: README
emoji: 📊
colorFrom: purple
colorTo: gray
sdk: static
pinned: false
Multilingual language models are typically large, requiring significant computational resources.
Can we create multilingual models that maintain performance comparable to their larger models while reducing size, latency and inference speeds?
Techniques:
- Pruning
- SparseGPT | GitHub
- ShortGPT | Perplexity Sensivities
- Knowledge Distillation
- DistillKit | GitHub
- Distil-Whisper based method
- On policy distillation of language models
- Minitron: Compact Language models via Pruning & Knowledge Distillation
- DistiLLM: Towards Streamlined Distillation for Large Language Models
- Quantization
- Fine-Tuning | GitHub
Dataset: Initial 7 datasets unified, having 6.62M rows which includes the following:
- Bangla_Alpaca_Orca : Bangle
- Urdu_Instruct_News_Article_Generation: Urdu
- Urdu_Instruct_News_Headline_Generation: Urdu
- Urdu_Instruct_News_Category_Classification: Urdu
- cidar: Arabic
- Six_Millions_Instruction_Dataset_For_Arabic_Llm_Ft: Arabic
- instructv3: English