petals
LLM runner
Enables users to fine-tune and run large language models on their own computers or in distributed networks.
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
9k stars
95 watching
525 forks
Language: Python
last commit: 4 months ago bloomchatbotdeep-learningdistributed-systemsfalcongptguanacolanguage-modelslarge-language-modelsllamamachine-learningmixtralneural-networksnlppipeline-parallelismpretrained-modelspytorchtensor-parallelismtransformervolunteer-computing