This powerful multilingual model performs well in coding and mathematics.
Low latency for real-time customer service bots. 7. StableLM Zephyr 3B
This series of ultra-small models (1.8B) is designed by H2O.ai. Fine-tuned for chat and instructional following. tiny 10 github top
Designed for developer laptops and IoT integration.
Excellent reasoning and creative writing for its size. 5. Karpathy’s llama2.c This powerful multilingual model performs well in coding
Written by Andrej Karpathy, this repository is a minimalist approach. It allows training and running a Baby Llama model in pure C.
It made "tiny" versions of massive models accessible to everyone. 2. Microsoft Phi-Series StableLM Zephyr 3B This series of ultra-small models (1
The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. Fully open-source and highly compact.
This GitHub project explores models where weights are just -1, 0, or 1.