view post Post 1848 Reply Wrote a blog post with some ideas about prompt engineering https://huggingface.co/blog/KnutJaegersberg/first-principles-prompt-engineering
view post Post 2226 Reply mobiuslabsgmbh/Llama-3.1-70b-instruct_4bitgs64_hqq99% of the performance across various benchmarks! mobiuslabsgmbh/Llama-3.1-70b-instruct_4bitgs64_hqq
Performance LLMs - Base Models Qwen/Qwen1.5-0.5B Text Generation • Updated Apr 5 • 219k • 138 stabilityai/stablelm-2-1_6b Text Generation • Updated Jul 10 • 12.7k • 177 openbmb/MiniCPM-2B-128k Text Generation • Updated May 24 • 2.66k • 37 stabilityai/stablelm-3b-4e1t Text Generation • Updated Mar 7 • 17.8k • 305
Performance LLMs - Fine tuned KnutJaegersberg/Qwen2-Deita-500m Text Generation • Updated Jun 6 • 109 • 4 KnutJaegersberg/Deita-2b Text Generation • Updated Mar 4 • 78 • 2 microsoft/Phi-3-mini-128k-instruct Text Generation • Updated 1 day ago • 285k • 1.55k NousResearch/Hermes-2-Pro-Mistral-7B Text Generation • Updated Jul 5 • 17.5k • 480