Peter-Devine
An AI engineer/developer at @lightblue-tech in Tokyo with a particular interest in natural language processing.
Peter-Devine's Stars
huggingface/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
ggerganov/llama.cpp
LLM inference in C/C++
hiyouga/LLaMA-Factory
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
salesforce/LAVIS
LAVIS - A One-stop Library for Language-Vision Intelligence
axolotl-ai-cloud/axolotl
Go ahead and axolotl questions
HazyResearch/metal
Snorkel MeTaL: A framework for training models with multi-task weak supervision
Digitous/ModelREVOLVER
Model REVOLVER, a human in the loop model mixing system.
HazyResearch/snorkel-superglue
Applying Snorkel to SuperGLUE
lightblue-tech/shitsu
A fast multilingual text quality classifier
changx03/adversarial_attack_defence
a Python framework for defending machine learning models from adversarial examples.
pierreandrieu/corankco
https://pypi.org/project/corankco/