SHYAM SUNDER KUMAR's repositories
MLInterview
:octocat: A curated awesome list of AI Startups in India & Machine Learning Interview Guide. Feel free to contribute!
MLCompetitions
:bowtie: Machine Learning Competition Codes
Indic-Languages-Wav2Vec
This contains Indian Languages Wav2Vec2 Implementation and details. Work in progress. !!
MLProjects
Machine Learning Projects
chat-ui
Open source codebase powering the HuggingChat app
chat-with-website
Simple Streamlit and Chainlit app to have interaction with your website URL.
genai_projects
Experiements on genai and agentic workflows
generative-ai-for-beginners
18 Lessons, Get Started Building with Generative AI đź”— https://microsoft.github.io/generative-ai-for-beginners/
knowledge_gpt
Accurate answers and instant citations for your documents.
langchain-tutorials
Overview and tutorial of the LangChain Library
LLM-workshop-2024
A 4-hour coding workshop to understand how LLMs are implemented and used
LLM_agents
Everything related to LLM based AI Agents
LLMs-from-scratch
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
machine-learning-for-trading
Code for Machine Learning for Algorithmic Trading, 2nd edition.
multimodal-live-api-web-console
A react-based starter app for using the Multimodal Live API over websockets with Gemini
OpenChat
Run and create custom ChatGPT-like bots with OpenChat, embed and share these bots anywhere, the open-source chatbot console.
quivr
Dump all your files and thoughts into your GenerativeAI Second Brain and chat with it
RAG-chat-with-documents
Chainlit app for advanced RAG. Uses llamaparse, langchain, qdrant and models from groq.
RAG_Techniques
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and contextually rich responses.
smol-course
A course on aligning smol models.
unsupervised_NER
Self-supervised NER prototype - updated version (69 entity types - 17 broad entity groups). Uses pretrained BERT models with no fine tuning. State-of-art performance on 3 biomedical datasets
wav2vec-toolkit
A collection of scripts to preprocess ASR datasets and finetune language-specific Wav2Vec2 XLSR models