VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct

VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct is an 8 billion parameter Llama-3-based instruction-tuned language model developed jointly by VAGO Solutions and Hyperspace.ai. This model is fine-tuned using DPO with curated German data, significantly enhancing its capabilities in both German and English. It is optimized for general conversational tasks and demonstrates strong performance across various benchmarks, including a German RAG LLM Evaluation score of 0.910.

Warm
Public
8B
FP8
8192
License: llama3
Hugging Face

No reviews yet. Be the first to review!