Riccardo Orlando's starred repositories
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
LLaMA2-Accessory
An Open-source Toolkit for LLM Development
instructor-embedding
[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings
keras-core
A multi-backend implementation of the Keras API, with support for TensorFlow, JAX, and PyTorch.
tinyvector
A tiny nearest-neighbor embedding database built with SQLite and Pytorch. (In development!)
tokenmonster
Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript
neurips_llm_efficiency_challenge
NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day
optimum-benchmark
A unified multi-backend utility for benchmarking Transformers, Timm, PEFT, Diffusers and Sentence-Transformers with full support of Optimum's hardware optimizations & quantization schemes.
soshiki-ios
The iOS Frontend for Soshiki
simple-generation
A python package to run inference with HuggingFace language and vision-language checkpoints wrapping many convenient features.
tagged-pile
Part-of-Speech Tagging for the Pile and RedPajama
llama-trainer
Llama Trainer Utility
aclpubcheck-gui
Graphical User Interface for aclpubcheck
exploring-srl
Repository for the paper "Exploring Non-Verbal Predicates in Semantic Role Labeling: Challenges and Opportunities"