Tatsu's shared repositories

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

alpaca_eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

alpaca_farm

A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.

gpt_paper_assistant

GPT4 based personalized ArXiv paper assistant bot

opinions_qa

test_set_contamination

conformal-factual-lm

linguistic_calibration

Align your LM to express calibrated verbal statements of confidence in its long-form generations.

mlm_inductive_bias

Code Release for "On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies"

fast_imagenet_ffcv

Fast ImageNet training code with FFCV