Stephen Fernandes's starred repositories
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.
ml-engineering
Machine Learning Engineering Open Book
Red-Teaming-Toolkit
This repository contains cutting-edge open-source security tools (OST) for a red teamer and threat hunter.
LLaMA-Adapter
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
tree-of-thought-llm
[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models
CTranslate2
Fast inference engine for Transformer models
attention_sinks
Extend existing LLMs way beyond the original training length with constant memory usage, without retraining
tpu-starter
Everything you want to know about Google Cloud TPU
LaMDA-rlhf-pytorch
Open-source pre-training implementation of Google's LaMDA in PyTorch. Adding RLHF similar to ChatGPT.
pytorch_memonger
Experimental ground for optimizing memory of pytorch models
llm-seminar
Seminar on Large Language Models (COMP790-101 at UNC Chapel Hill, Fall 2022)
Squeezeformer
[NeurIPS'22] Squeezeformer: An Efficient Transformer for Automatic Speech Recognition
electra-pytorch
A simple and working implementation of Electra, the fastest way to pretrain language models from scratch, in Pytorch
IndicTrans2
Translation models for 22 scheduled languages of India
FEP_Active_Inference_Papers
A repository for major/influential FEP and active inference papers.
openai_trtllm
OpenAI compatible API for TensorRT LLM triton backend
flacuna
Flacuna was developed by fine-tuning Vicuna on Flan-mini, a comprehensive instruction collection encompassing various tasks. Vicuna is already an excellent writing assistant, and the intention behind Flacuna was to enhance Vicuna's problem-solving capabilities. To achieve this, we curated a dedicated instruction dataset called Flan-mini.
Distributed-Multi-Video-Streaming-and-Processing-with-Kafka
Stream and process multiple videos in near real time using Kafka. The video frames are processed and a machine learning model does inference on them and the results are stored in a mongodb database.
PyTorch-Elmo-BiLSTMCRF
PyTorch BiLSTMCRF w Elmo
unify-learning-paradigms
data collator for UL2 and U-PaLM
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.
slam_with_vit
Visual SLAM for Mobile Robots with Vision Transformer(ViT)