Breast Cancer Predictor

The Breast Cancer Diagnosis app is a machine learning-powered tool designed to assist medical professionals in diagnosing breast cancer.

ChatPDF

Built a Document chatbot using latest best in class technologies langchain, openAI LLM, streamlit etc

Finetune T5 Model for Summarization task

Refer to colab notebook link provided - Fine tune the T5 model on xsum dataset - Using hugging face transformers libraries and datasets for both dataset download and training the model

Prompt generator based on short description

The use case Using single/few words model has to generate prompts that we can give it to ChatGPT as context, so it will take up the role you defined for chat context - Finetuned "facebook/bart-large" model on Awesome ChatGPT Prompts dataset - The resulting model is able to generate good prompts

English to Hindi Translator model

Train a model which will translate sentences from English to Hindi language

QLoRa: Fine-Tune a Large Language Model("EleutherAI/gpt-neox-20b") on Single GPU

Fine-tuning models with billions of parameters is now possible on consumer hardware Most large language models (LLM) are too big to be fine-tuned on consumer hardware. For instance, to fine-tune a 65 billion parameters model we need more than 780 Gb of GPU memory. This is equivalent to ten A100 80

GPT3.5 prompt based Legal expert chat bot

More related to prompt engineering Charaicter had asked to create few prompt based charecters GPT3.5 prompt based chat bot which takes persona of Legal expert

GPT3.5 based Elon Musk Persona

On request of company charaicter.com created this charaicter This is more of prompt engineering on backend OpenAI GPT3.5 is called for chat

stable-diffusion model inference

In this notebook we're going to go over how to set up the Stability SDK package, and how to use our API to perform a basic inference call.

Image generation using two methods viz OpenAI's DALLE and Hugging-Faces's Diffusers model

An AI-based image generation app built using Streamlit, Open AI's DALL-E, and huggingface diffusers.

Aspect-Based Sentiment Analysis (ABSA) using PyABSA

Aspect-Based Sentiment Analysis (ABSA) provides a more granular and insightful understanding of opinions expressed in text data. By identifying aspects and analyzing sentiments associated with them, ABSA enables fine-grained opinion mining in various domains such as product reviews, social media ana

Auto label (using GroundedSAM) to create dataset from videos and use the auto labelled dataset to train faster yolov8 model

- Pick some video files - Split the video files into frames and store it in images directory - Feed the images directory into GroundedSAM with CaptionOntology i.e you define labels - Auto labelling will be done stored in dataset - Use the dataset to train Yolov8 model

Zero Shot Object Detection With GroundingDINO

Use GroundingDino weights to do zero shot predictions using text prompt labels provided

Fine-tune Falcon-7B on Your GPU with TRL and QLoRa.

The Falcon models are state-of-the-art LLMs. They even outperform Meta AI’s LlaMa on many tasks. Even though they are smaller than LlaMa, fine-tuning the Falcon models still requires top-notch GPUs with more than 40 GB of VRAM. Well, this was before the introduction of QLoRa. QLoRa quantizes LLMs

Train DETR with Hugging-Face Transformers on a Custom Dataset

In this notebook, we are going to fine-tune DETR (end-to-end object detection with Transformers) on a custom object detection dataset.

MASSIVELY MULTILINGUAL SPEECH (MMS) MODEL, SPEECH TO TEXT AND TEXT TO SPEECH

Meta, the company that owns Facebook, released a new AI model called Massively Multilingual Speech (MMS) that can convert text to speech and speech to text in over 1,100 languages