petals
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
- 11k
- Python
- MIT
- 2 y ago
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.
Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback
Fraud detection with the Paysim financial dataset, Neo4j Graph Data Science, and Neo4j Bloom
Text generation model, used with transformers.