In this repo, I'll try to create a chatbot using Streamlit. The model I'll be using will be BART-base finetuned on Bitext-customer-support-llm-chatbot-training-dataset.

Synthetic Data Generator for ML Applications

Reading PaliGemma paper ...

Making of cuda kernel

Material for gpu-mode lectures

LLM training in simple, raw C/CUDA

LLM101n: Let's build a Storyteller

Building GPT ...

Working on the implementation of ORPO

Train transformer language models with reinforcement learning.

Foundational Models for State-of-the-Art Speech and Text Translation

You will learn about RLHF from this repository 🤖.

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024

Reference implementation of Mistral AI 7B v0.1 model.

Embedding Studio is a framework which allows you transform your Vector Database into a feature-rich Search Engine.

Complete implementation of Llama2 with/without KV cache & inference 🚀

Port of OpenAI's Whisper model in C/C++

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Best practices for distilling large language models.

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…

Implementation of the Transformer model from the paper Attention Is All You Need in Pytorch.

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

Effort to open-source NLLB checkpoints.

Language-Agnostic SEntence Representations

Implementation of Meta-Voicebox : The first generative AI model for speech to generalize across tasks with state-of-the-art performance.

I am sharing my Journey of 300DaysOfData in Machine Learning and Deep Learning.

🦜🔗 Build context-aware reasoning applications

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Personal website for Thinam Tamang