Owaiskhan9654
I am a data scientist; I love to analyze data for trends and patterns and interpret data with a clear objective in mind and build scalable data pipelines.
IBMBengaluru, Karnataka, India
Pinned Repositories
Clinical-Trial-Article-Search
Search using Attention based Sentence Transformers
Covid-19-Prognosis
Early diagnosis is the single most important factor when determining any disease outcomes. Two thirds of diseases can be cured if diagnosed early. Canary uses proven biomarkers and proprietary Nano Sensors to map and uncover hidden data in your breath, so Covid-19,Cancers and other diseases can be detected early and treated more successfully.
Gene-Sequence-Primer-
Gene and Primer Sequence Analysis for SARS-CoV-2, EGFR(Non Small Lung Cancer Cell), Influenza DNAs ### How can I check my Oligo primers to ensure there are no significant primer design issues? - The difference between melting temperatures (Tm) of the primers should be less than 5°C. - The GC content should be between 35-80% or equivalent to the product being amplified. - The Delta G value of any self-dimers, hairpins, and heterodimers should be weaker (more positive) than -9.0 kcal/mole. Positive numbers indicate that the actual secondary structure shown will not form at all. - Avoid 3' complementarity between the two primers to prevent primer dimers. The IDT OligoAnalyzer APIs can be used to assess these different criteria for a proposed oligo. #### [Reference](https://sg.idtdna.com/pages/support/faqs/how-can-i-check-my-pcr-primers-using-the-oligoanalyzer-program-to-ensure-there-are-no-significant-primer-design-issues-)
Hierarchical-Multi-Label-Text-Classification
The code of CIKM'19 paper《Hierarchical Multi-label Text Classification: An Attention-based Recurrent Network Approach》
Multi-Label-Classification-of-Pubmed-Articles
The traditional machine learning models give a lot of pain when we do not have sufficient labeled data for the specific task or domain we care about to train a reliable model. Transfer learning allows us to deal with these scenarios by leveraging the already existing labeled data of some related task or domain. We try to store this knowledge gained in solving the source task in the source domain and apply it to our problem of interest. In this work, I have utilized Transfer Learning utilizing BertForSequenceClassification model. Also tried RobertaForSequenceClassification and XLNetForSequenceClassification models for Fine-Tuning the Model.
owaiskhan9654
This repo contains my achievements and tracks my progress and contributions to open source community
Owaiskhan9654.github.io
Sony-R.I.S.E-India-Hackathon-3rd-Place-Solution
Recent Sony RISE Research Team India organized and this is my Solution in which I secured 3rd Position. Recommender systems are among the most popular applications of data science today. They are used to predict the "rating" or "preference" that a user would give to an item. In this Challenge I have computed and extracted several Features in order to Build this Hybrid Collaborative Recommender System
Team-PYPI-Blue-sky-challenge-HackerEarth-Hackathon-
Yolo-V7-Custom-Dataset-Train-on-Kaggle
Owaiskhan9654's Repositories
Owaiskhan9654/Multi-Label-Classification-of-Pubmed-Articles
The traditional machine learning models give a lot of pain when we do not have sufficient labeled data for the specific task or domain we care about to train a reliable model. Transfer learning allows us to deal with these scenarios by leveraging the already existing labeled data of some related task or domain. We try to store this knowledge gained in solving the source task in the source domain and apply it to our problem of interest. In this work, I have utilized Transfer Learning utilizing BertForSequenceClassification model. Also tried RobertaForSequenceClassification and XLNetForSequenceClassification models for Fine-Tuning the Model.
Owaiskhan9654/Gene-Sequence-Primer-
Gene and Primer Sequence Analysis for SARS-CoV-2, EGFR(Non Small Lung Cancer Cell), Influenza DNAs ### How can I check my Oligo primers to ensure there are no significant primer design issues? - The difference between melting temperatures (Tm) of the primers should be less than 5°C. - The GC content should be between 35-80% or equivalent to the product being amplified. - The Delta G value of any self-dimers, hairpins, and heterodimers should be weaker (more positive) than -9.0 kcal/mole. Positive numbers indicate that the actual secondary structure shown will not form at all. - Avoid 3' complementarity between the two primers to prevent primer dimers. The IDT OligoAnalyzer APIs can be used to assess these different criteria for a proposed oligo. #### [Reference](https://sg.idtdna.com/pages/support/faqs/how-can-i-check-my-pcr-primers-using-the-oligoanalyzer-program-to-ensure-there-are-no-significant-primer-design-issues-)
Owaiskhan9654/owaiskhan9654
This repo contains my achievements and tracks my progress and contributions to open source community
Owaiskhan9654/Sony-R.I.S.E-India-Hackathon-3rd-Place-Solution
Recent Sony RISE Research Team India organized and this is my Solution in which I secured 3rd Position. Recommender systems are among the most popular applications of data science today. They are used to predict the "rating" or "preference" that a user would give to an item. In this Challenge I have computed and extracted several Features in order to Build this Hybrid Collaborative Recommender System
Owaiskhan9654/Statistical-Inference-Multivariate-Techniques-Python-Implementation
Python Implementation
Owaiskhan9654/Web-Scraping-from-Used-Car-website-in-UAE-Region
Here I am Scraping data from https://www.drivearabia.com/ and this code is in sync with the website currently (FEB 2023).
Owaiskhan9654/Autogen-Kaggle
Owaiskhan9654/llm.c
LLM training in simple, raw C/CUDA
Owaiskhan9654/AgentSmiths
llm intergration with multiagent systems for webdev solutions
Owaiskhan9654/autogen
Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ
Owaiskhan9654/cognitive-services-speech-sdk-js
Microsoft Azure Cognitive Services Speech SDK for JavaScript
Owaiskhan9654/docling
Get your documents ready for gen AI
Owaiskhan9654/langchain
⚡ Building applications with LLMs through composability ⚡
Owaiskhan9654/self-rag
This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.
Owaiskhan9654/torchserve-embedder-encoder
Embeddings Microservice for use in various projects
Owaiskhan9654/Transformer-from-scratch
Owaiskhan9654/Awesome-LLMOps
An awesome & curated list of best LLMOps tools for developers
Owaiskhan9654/elasticsearch-test-elser
Owaiskhan9654/experimental-code-assistant
Owaiskhan9654/FlashRank
Ultra-lite & Super-fast SoTA cross-encoder based re-ranking for your search & retrieval pipelines. Created by Prithivi Da, open for PRs & Collaborations.
Owaiskhan9654/GPTs
leaked prompts of GPTs
Owaiskhan9654/h2o-llmstudio
H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://h2oai.github.io/h2o-llmstudio/
Owaiskhan9654/itz-support-public
A public Repository for Runbooks and Documentation for DTE Content on the IBM Technology Zone. Available to Business Partners and IBMers looking for self service support. Current Runbooks provide support the the IBM Technology Zone website, Skytap, ROKS, and Common Control Plane based Demos.
Owaiskhan9654/llama-recipes
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
Owaiskhan9654/llama3v
A SOTA vision model built on top of llama3 8B.
Owaiskhan9654/monday-cli-ibm
A Python Client for Monday.com
Owaiskhan9654/Outcomes-Projects
Repository of demo projects
Owaiskhan9654/primeqa
The prime repository for state-of-the-art Multilingual Question Answering research and development.
Owaiskhan9654/QueryCraft
The simplest and most comprehensive framework for building enterprise-grade NL2SQL GenAI applications at scale.
Owaiskhan9654/test_test