Mabeck/Heidrun-Mistral-7B-chat

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Feb 13, 2024License:mitArchitecture:Transformer0.0K Open Weights Cold

Heidrun-Mistral-7B-chat is a 7 billion parameter chat model developed by Mabeck, fine-tuned from Heidrun-Mistral-7B-base with a 4096-token context length. It is specifically optimized for Danish language tasks, demonstrating strong performance in logic and reasoning. This model ranks as a leading open-source Danish LLM on the ScandEval benchmark, making it ideal for applications requiring high-quality Danish language understanding and generation.

Loading preview...

Heidrun-Mistral-7B-chat: A Leading Danish LLM

Heidrun-Mistral-7B-chat, developed by Mabeck, is a 7 billion parameter chat model fine-tuned from Heidrun-Mistral-7B-base. It leverages Danish instruction datasets like danish-OpenHermes and skoleGPT to excel in conversational AI for the Danish language. This model was trained efficiently using Unsloth and Huggingface's TRL library.

Key Capabilities

  • SOTA Danish Performance: Ranks 1st among Danish open-source LLMs on the ScandEval benchmark, also sharing 1st place across all Scandinavian languages.
  • Strong Logic and Reasoning: Demonstrates robust performance in logic and reasoning tasks within the Danish language context.
  • ChatML Format: Optimized for the ChatML format, ensuring best performance when used with this specific structure.

Benchmarks

Evaluated using ScandEval, Heidrun-Mistral-7B-chat shows competitive results:

  • MMLU-da: 35.66% (ranks 3rd)
  • DANSK: 50.80% (ranks 3rd=)
  • Hellaswag-da: 29.18% (ranks 4th)

Good for

  • Developing Danish-language chatbots and conversational agents.
  • Applications requiring high-quality Danish text generation and understanding.
  • Research and development in Scandinavian natural language processing, particularly for Danish.