chiphuyen
Follow
Cool LLM repos
Used for adaptive human in the loop evaluation of language and embedding models.
Superduper: Build end-to-end AI applications and agent workflows on your existing data infrastructure and preferred tools - without migrating your data.
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
Open-Source Reproduction/Demo of the LLM Riddles Game
Convert Machine Learning Code Between Frameworks
Large Language Model Text Generation Inference
New ways of breaking app-integrated LLMs
A library of data loaders for LLMs made by the community -- to be used with LlamaIndex and/or LangChain
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”
A Unified Library for Parameter-Efficient and Modular Transfer Learning
ModelScope: bring the notion of Model-as-a-Service to life.
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
A collaboration friendly studio for NeRFs
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
QLoRA: Efficient Finetuning of Quantized LLMs
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
🩹Editing large language models within 10 seconds⚡
🎙️🤖Create, Customize and Talk to your AI Character/Companion in Realtime (All in One Codebase!). Have a natural seamless conversation with AI everywhere (mobile, web and terminal) using LLM OpenAI …
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
InternGPT (iGPT) is an open source demo platform where you can easily showcase your AI models. Now it supports DragGAN, ChatGPT, ImageBind, multimodal chat like GPT-4, SAM, interactive image editin…
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters