Jorge Grisman's Projects
Train an NLP model using transformers and datasets library together with a custom Amazon sagemaker-sdk to detect adverse drugs effects
Building-and-Evaluating-Advanced-RAG-Applications Deeplearning AI Course
This repository hosts the source code for a memory-enhanced chatbot application, utilizing Amazon Bedrock (Claude 3 Haiku), LangChain, Faiss, and Streamlit technologies.
This sequential models based approach to predict the sentiment over a movie review using the IMDB movie reviews dataset. The kernel imports the IMDB reviews (originally text - already transformed by Keras to integers using a dictionary).
I'd like to share my journey through DeepLearning.AI's Course in Functions, Tools and Agents with LangChain.
Tutorials on how knowledge graphs works, how to build with them, and create better retrieval augmented generation applications with the help of knowledge graphs.
LangChain for LLM Application Development course notebooks
I'd like to share my journey through DeepLearning.AI's Course in Vector Databases: from Embeddings to Applications.
Evaluating large language models (LLM) is challenging due to their broad capabilities and the inadequacy of existing benchmarks in measuring human preferences. To address this, strong LLMs are used as judges to evaluate these models on more open-ended questions.
algoexamplesearch
Notebook to fine-tune-falcon7b model in sag.
Ultra-lite & Super-fast re-ranking for your search & retrieval pipelines. Based on SoTA models like cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.
Collection of leaked system prompts
Collection of training scripts for supervised fine-tuning and alignment of transformer language models. The scripts are designed to be run on Amazon SageMaker for efficient training of large language models.
A mental health chatbot designed to provide support and resources for individuals seeking help.
PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538
Machine Learning Engineer on Udacity content with projects and code.
multi-label classification techniques using the toxic comments dataset.
My projects and work with scripts on Udacity's Natural Language Processing Nanodegree
This repo shows a set folder with notebooks demonstrating a variety techniques with different approaches for developing recommendation systems.
train an NLP model using transformers and datasets library together with a custom Amazon sagemaker-sdk
Rust project that provides a quick functionality for loading CSV data into a Polars dataframe, which is a data manipulation and analysis library in Rust. With this library, users can easily and efficiently load, transform, and analyze large datasets in Rust.
Rust program that uses the csv crate to read a CSV file and store its data in memory. The main function of the program calls the "read_csv" function, which creates a "Reader" object using the path to the CSV file.
Selenium web browser automation to find cheapest flight for my trip to Rome.
This repository contains some notebooks of modeling steps that I use when dealing with time series data.