lukaemon Goto Github PK

coursera-ml-andrewng

use numpy, scipy, and tensorflow to implement these basic ML model and learning algorithm

hackathon

llama-recipes

Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger

lukaemon.github.io

mistral-src

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

moondream

tiny vision language model

nanogpt

The simplest, fastest repository for training/finetuning medium-sized GPTs.

prismatic-vlms

A flexible and efficient codebase for training visually-conditioned language models (VLMs)

tensor-puzzles

Solve puzzles. Improve your pytorch.

tensor_puzzle

Practice tensor ops in first principle.

vila

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)