Pinned Repositories
templates
dpo-prefix-sharing
DPO, but faster 🚀
roebling
Load Testing Tool using Haskell
attendance-system
A facial recognition based attendance system; Summer School 2018
cuda-resource-stream
CUDA related news and material links
peft
Fork of 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning. Our implementation for IA3, a new fine-tuning method is now a part of the official Huggingface library!
python-mastery
My solutions for Advanced Python Mastery (course by @dabeaz)
text-to-meme
A Text to Meme model that can generate a full meme given user text.
tokenization
A comprehensive deep dive into the world of tokens
deep-atrous-guided-filter
Deep Atrous Guided Filter for Image Restoration in Under Display Cameras (UDC Challenge, ECCV 2020).
SumanthRH's Repositories
SumanthRH/tokenization
A comprehensive deep dive into the world of tokens
SumanthRH/python-mastery
My solutions for Advanced Python Mastery (course by @dabeaz)
SumanthRH/text-to-meme
A Text to Meme model that can generate a full meme given user text.
SumanthRH/cuda-resource-stream
CUDA related news and material links
SumanthRH/pygloo
Pygloo provides Python bindings for Gloo.
SumanthRH/TuPaTE
Code for EMNLP 2022 paper "Efficiently Tuned Parameters are Task Embeddings"
SumanthRH/accelerate
🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
SumanthRH/AdapNet-pp
Code for the EE6132 Course Project, Fall 2019. Code forked from https://github.com/DeepSceneSeg/AdapNet-pp with project-specific changes
SumanthRH/Chain-of-ThoughtsPapers
A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models".
SumanthRH/chatbot-deployment
Deployment of PyTorch chatbot with Flask
SumanthRH/peft
Fork of 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning. Our implementation for IA3, a new fine-tuning method is now a part of the official Huggingface library!
SumanthRH/cudamodelecture1
SumanthRH/ecco
Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, BERT, RoBERTA, T5, and T0).
SumanthRH/entropix
Entropy Based Sampling and Parallel CoT Decoding
SumanthRH/FastChat
Fork of FastChat, an open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.
SumanthRH/ia_3_test
Fork of Chao's test with peftt ia^3. Trying to get to the bottom of IA3 training errors.
SumanthRH/ICL_Support_Example
The official implementation of the paper "Finding Support Examples for In-Context Learning".
SumanthRH/Liger-Kernel
Efficient Triton Kernels for LLM Training
SumanthRH/llmperf
LLMPerf is a library for validating and benchmarking LLMs
SumanthRH/lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
SumanthRH/nanotron
Minimalistic large language model 3D-parallelism training
SumanthRH/personal-website
My personal website, built on top of Wowchemy
SumanthRH/ray
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
SumanthRH/starter-hugo-academic
🎓 Hugo Academic Theme 创建一个学术网站. Easily create a beautiful academic résumé or educational website using Hugo, GitHub, and Netlify.
SumanthRH/SumanthRH
SumanthRH/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
SumanthRH/trl
Train transformer language models with reinforcement learning.
SumanthRH/ulogme
Automatically collect and visualize usage statistics in Ubuntu/OSX environments.
SumanthRH/unsloth
5X faster 50% less memory LLM finetuning
SumanthRH/wowchemy-hugo-themes
🔥 Hugo website builder, Hugo themes & Hugo CMS. No code, easily build with blocks! 创建在线课程，学术简历或初创网站。#OpenScience