Fariz Ikhwantri's starred repositories
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
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
curated-transformers
🤖 A PyTorch library of curated Transformer models and their composable components
the-story-of-heads
This is a repository with the code for the ACL 2019 paper "Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned" and the ACL 2021 paper "Analyzing Source and Target Contributions to NMT Predictions".
Diffusion-BERT
ACL'2023: DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models
Physics-Aware-Training
Instructional implementation of Physics-Aware Training (PAT) with demonstrations on simulated experiments.
eraserbenchmark
A benchmark for understanding and evaluating rationales: http://www.eraserbenchmark.com/
jestimator
Amos optimizer with JEstimator lib.
backpacks-flash-attn
The original Backpack Language Model implementation, a fork of FlashAttention
torchscale
Transformers at any scale
time_interpret
Unified Model Interpretability Library for Time Series
tokenizations
Robust and Fast tokenizations alignment library for Rust and Python https://tamuhey.github.io/tokenizations/
learning-scaffold
This is the official implementation for the paper "Learning to Scaffold: Optimizing Model Explanations for Teaching"
robust-attribution-regularization
Robust Attribution Regularization
WebQAmGaze
WebQAmGaze, a multilingual low-cost eye-tracking dataset (using webgazer)