- LLM training handbook : https://github.com/huggingface/llm_training_handbook
- HF model/dataset downloading : https://github.com/bodaay/HuggingFaceModelDownloader
- Dataset curation : https://github.com/taylorai/galactic
- mergekit : https://github.com/cg123/mergekit
- Running LLM locally (ollama) : https://github.com/jmorganca/ollama
- Training tokenizer on top of an existing one : https://huggingface.co/learn/nlp-course/chapter6/2?fw=pt
- MoE training : https://github.com/mistralai/megablocks-public
- GPU poor (resource checker) : https://rahulschand.github.io/gpu_poor/
naubull2 / llm-primers Goto Github PK
View Code? Open in Web Editor NEWMultiple out-sources and scripts for harnessing LLMs quickly