Kush Blogs
Latest Writings
-
11. NLP: Tokenizers
A detailed description about tokenizers in LLMs.#NLP
-
10. NLP: Mixture of Experts (MOE)
A guide on Mixture of Experts with their history and implementation in transformers along with the losses associated with it.#NLP
-
9. NLP: Optimizing Attention
A guide on KV-Caching along with Sliding Window Attention. Ending with MQA and GQA.#NLP
-
8. NLP: BERT
A guide on BERT models and how their architecture.#NLP
-
7. NLP: Transformer Implementation
Implementation and trainig of Transformer for En-Hi machine translation task.#NLP #Transformers
-
6. NLP: Transformers
A complete guide to the transformer architecture, attention mechanisms, and positional encoding.#NLP #Transformers
-
5. NLP: Attention
A guide on Attention mechanism for seq2seq models.#NLP
-
4. NLP: Seq2Seq
A guide on Seq2Seq models that changed machine translation task.#NLP
-
3. NLP: Pytorch for NLP
Some tips for working with PyTorch for NLP tasks#NLP
-
2. NLP: Long Short Term Memory [LSTM] & Gated Recurrent Unit [GRU]
A guide on LSTM and GRU models and how they overcome limitations of RNNs.#NLP
-
1. NLP: Recurrent Neural Networks [RNN]
A guide on the first steps towards modern NLP.#NLP