Sourab Mangrulkar

LLM-Workshop. LLM Workshop by Sourab Mangrulkar

openhathi_instruct. This repository contains the code for dataset curation and finetuning of instruct variant of the Bilingual OpenHathi model. The resulting model is meant to follow instructions and chat in Hindi and Hinglish.

peft-codegen-25. Python

accelerate-deepspeed-test. Testing DeepSpeed integration in 🤗 Accelerate

mlc-llm. Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

accelerate-megatron-test. Testing the accelerate megatron integration

peft-sd-webui-additional-networks. Python

accelerate-aws-sagemaker. Examples showcasing AWS SageMaker integration of 🤗 Accelerate. Just give the `accelerate config` and do `accelerate launch` 🚀. As simple as that!

acm_winter_school_gen_ai. Code for the hands-on projects for the students attending the ACM India Winter School 2023

Machine_Learning. Machine Learning models for Regression Tasks and Classification Tasks.

devika. Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.

pacman100.

Know-It-Owl-A-Question-Answering-Chatbot. A chatbot that uses Machine Reading Comprehension (MRC) for question answering.

Extractive-Text-Summarization-Using-Neural-Networks. Extractive Text Summarization Using Neural Networks approaches: CNN, RNN and Linear-SVM

pacman100.github.io. Dockerfile

ram_efficient_fsdp. Python

twinny. The most no-nonsense locally hosted (or API hosted) AI code completion plugin for Visual Studio Code, like GitHub Copilot but 100% free and 100% private.

AI-Avatar. My personal AI Avatar

llm.c. LLM training in simple, raw C/CUDA

torchtune. PyTorch native finetuning library

gpt-fast. Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

peft-dreambooth-ui. An UI for Dreambooth training and inference using PEFT - Minimal, Easy to use and Adaptable.

transformers. 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

peft-whisper-large. Python

accelerate. 🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

peft-dreambooth. Python

alpaca-lora. Instruct-tune LLaMA on consumer hardware

temp. Jupyter Notebook

datasets. 🤗 Fast, efficient, open-access datasets and evaluation metrics in PyTorch, TensorFlow, NumPy and Pandas