-
Tokenization, Case-folding, Stop-word Removal, Stemming, Lemmatization, Parts-of-Speech Tagging, Named Entity Recognition, Parsing Notebook-> NLP_preprocessing.ipynb
-
Bag of Words, Cosine Similarity, TF-IDF Notebook-> BOW_TF-IDF.ipynb
-
Word Vectors, Word2Vec, PCA, Google News Vectors, Sentiment Analysis on YELP (Keras) Notebook -> Word_vectors.ipynb
-
Building a NLP classifier on the News20 dataset (Keras) Notebook->Neural_Network_Classifier.ipynb
-
Transformers for Scratch Building a charcter level GPT using Mini Shakespeare data Nootbook->gpt-dev-viz.ipynb
- Fine-tuning a Pegasus Model on SAMSum Dataset. Notebook->Text_Summarizer_Pegasus.ipynb
- Topic Modelling using Latent Dirichlet Allocation (LDA) Notebook->topic_modelling_lda.ipynb
Colab Notebook->Topic Modelling using LDA
-
Llama 2
-
Langchain
-
RAG
-
MLflow project