view post Post 968 Reply appvoid/arcoarco consistently outperforms every sota model below 600m parameters on average appvoid/arco
view post Post 2028 Reply Wrote a blog post with some ideas about prompt engineering https://huggingface.co/blog/KnutJaegersberg/first-principles-prompt-engineering
Performance LLMs - Base Models Qwen/Qwen1.5-0.5B Text Generation • Updated Apr 5 • 750k • 142 stabilityai/stablelm-2-1_6b Text Generation • Updated Jul 10 • 12.2k • 180 openbmb/MiniCPM-2B-128k Text Generation • Updated May 24 • 2.56k • 41 stabilityai/stablelm-3b-4e1t Text Generation • Updated Mar 7 • 87.3k • 307
Performance LLMs - Fine tuned KnutJaegersberg/Qwen2-Deita-500m Text Generation • Updated Jun 6 • 11 • 4 KnutJaegersberg/Deita-2b Text Generation • Updated Mar 4 • 52 • 2 microsoft/Phi-3-mini-128k-instruct Text Generation • Updated Aug 20 • 247k • 1.58k NousResearch/Hermes-2-Pro-Mistral-7B Text Generation • Updated 23 days ago • 16.5k • 480