view post Post 1132 Reply appvoid/arcoarco consistently outperforms every sota model below 600m parameters on average appvoid/arco
view post Post 2210 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 • 329k • 143 stabilityai/stablelm-2-1_6b Text Generation • Updated Jul 10 • 17.6k • 186 openbmb/MiniCPM-2B-128k Text Generation • Updated May 24 • 674 • 41 stabilityai/stablelm-3b-4e1t Text Generation • Updated Mar 7 • 12k • 309
Performance LLMs - Fine tuned KnutJaegersberg/Qwen2-Deita-500m Text Generation • Updated Jun 6 • 7 • 4 KnutJaegersberg/Deita-2b Text Generation • Updated Mar 4 • 75 • 2 microsoft/Phi-3-mini-128k-instruct Text Generation • Updated Aug 20 • 748k • 1.61k NousResearch/Hermes-2-Pro-Mistral-7B Text Generation • Updated Sep 8 • 16.4k • 487
KnutJaegersberg/WizardLM_evol_instruct_V2_196k_instruct_format Preview • Updated Sep 4, 2023 • 40 • 3