Models and examples built with TensorFlow

fast python port of arc90's readability tool, updated to match latest readability.js!

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Quantized inference code for LLaMA models

python implementation of the parquet columnar file format.

⏩ Generating speech in a single forward pass without any attention!

A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick

Pyink, pronounced pī-ˈiŋk, is a Python formatter, forked from Black with a few different formatting behaviors.

Pytorch Implementation of ALBERT(A Lite BERT for Self-supervised Learning of Language Representations)

XLNet: fine tuning on RTX 2080 GPU - 8 GB

Training Transformer-XL on 128 GPUs

NYU ML² work on sentence encoding with tree structure and dynamic graphs

GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ

AdaRFT: Efficient Reinforcement Finetuning via Adaptive Curriculum Learning

Assessing syntactic abilities of BERT

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Real-time Attribution Classification to Detect Hallucinations