# Knowledge Distillation Model

This is a quantized version of a large language model, aiming to make knowledge more accessible and usable.

DeepSeek-R1-Distill-Llama-8B is an 8B-parameter large language model based on the Llama architecture, optimized through distillation training for text generation tasks.

A multilingual sentence embedding model based on sentence-transformers, specially optimized for Bengali, suitable for semantic similarity calculation and clustering analysis

This model is a fine-tuned version of distilbert-base-cased-distilled-squad, suitable for question-answering tasks

This is a question-answering model fine-tuned on the SQuAD v1.1 dataset using knowledge distillation techniques, based on the DistilBERT-base-cased model.

DistilGPT2 is a lightweight distilled version of GPT-2 with 82 million parameters, retaining GPT-2's core text generation capabilities while being smaller and faster.