Andrea Parker's repositories
alpaca_eval
A automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
Awesome-Deblurring
A curated list of resources for Image and Video Deblurring
awesome-machine-learning-in-compilers
Must read research papers and links to tools and datasets that are related to using machine learning for compilers and systems optimisation
awesome-NeRF
A (forked) curated list of awesome neural radiance fields papers - 2024-01
datashare
A self-hosted search engine for documents.
degoogle
A huge list of alternatives to Google products. Privacy tips, tricks, and links.
ECCV2022-RIFE
ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.
ggml
Tensor library for machine learning
gpt-engineer
Specify what you want it to build, the AI asks for clarification, and then builds it.
guidance
A guidance language for controlling large language models.
langfuse
Open source observability and analytics for LLM applications
LLaMA-Adapter
Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
llama-nuts-and-bolts
A holistic way of understanding how LLaMA and its components run in practice, with code and detailed documentation.
LLM-eval-survey
The official GitHub page for the survey paper "A Survey on Evaluation of Large Language Models".
llm_finetuning
Convenient wrapper for fine-tuning and inference of Large Language Models (LLMs) with several quantization techniques (GTPQ, bitsandbytes)
llms_on_smaller_hardware
A repo to house my misc notes, code, etc. on running LLMs on less powerful hardware
LLMSurvey
The official GitHub page for the survey paper "A Survey of Large Language Models".
Neural-Relation-Graph
Official PyTorch implementation of "Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data" (NeurIPS'23)
neural_networks_solomonoff_induction
Repo for https://arxiv.org/abs/2401.14953
Platypus
Code for fine-tuning Platypus fam LLMs using LoRA
raspi-thermal-cam
Raspberry Pi Thermal Camera in Real Time with MLX90640 and Python
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
scenic
Scenic: A Jax Library for Computer Vision Research and Beyond
WarpFactory
WarpFactory is a numerical toolkit for analyzing warp drive spacetimes.