Damien Tanner's starred repositories
LLaMA-Factory
Unify Efficient Fine-Tuning of 100+ LLMs
onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
transformers.js
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
google-indexing-script
Script to get your site indexed on Google in less than 48 hours
WeightWatcher
The WeightWatcher tool for predicting the accuracy of Deep Neural Networks
aphrodite-engine
PygmalionAI's large-scale inference engine
wishful-search
Natural language search for complex JSON arrays, with AI Quickstart.
ollama-voice-mac
Mac compatible Ollama Voice
prometheus
[ICLR 2024 & NeurIPS 2023 WS] An Evaluator LM that is open-source, offers reproducible evaluation, and inexpensive to use. Specifically designed for fine-grained evaluation on a customized score rubric, Prometheus is a good alternative for human evaluation and GPT-4 evaluation.
NeuScraper
This is the code repo for our paper "Cleaner Pretraining Corpus Curation with Neural Web Scraping".
min-max-gpt
Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
101-school
AI generated courses
MiniSearch
Minimalist web-searching app with an AI assistant that runs directly from your browser. Uses Web-LLM, Ratchet-ML, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space
Conda-autoactivate-env
Add autoactivate functionality on Conda. (Only Unix-based OS)
vram-calculator
Transformer GPU VRAM estimator