bineric/NorskGPT-Llama-13B-v0.1
bineric/NorskGPT-Llama-13B-v0.1 is a Norwegian variant of the Llama-2-13b-chat-hf model, fine-tuned on a curated dataset of Norwegian instruction pairs. This 13 billion parameter model is specifically designed to understand and generate text in Norwegian. It excels at tasks such as summarization, question answering, and chat within the Norwegian language context, making it suitable for assistant-like applications.
Loading preview...
Overview
bineric/NorskGPT-Llama-13B-v0.1 is a specialized language model derived from the Llama-2-13b-chat-hf architecture. Its primary distinction lies in its fine-tuning on a carefully selected mix of Norwegian instruction pairs, enabling it to understand and generate text proficiently in Norwegian.
Key Capabilities
- Norwegian Language Proficiency: Tuned specifically for Norwegian text generation and comprehension.
- Instruction Following: Designed to respond to instructions, making it suitable for assistant-like interactions.
- Chat Functionality: Capable of engaging in conversational exchanges.
- Summarization: Performs well on tasks requiring text summarization.
- Question Answering: Effective in answering questions based on provided context.
Intended Use & Limitations
This model is intended for personal and research use within the Norwegian language domain. It functions best as an assistant-like chat model. However, it's important to note that as an LLM, its knowledge about Norway is limited to its base model's training data and it is not a dedicated knowledge model. It generally performs better on generative tasks like summarization and chat rather than tasks requiring deep, specific domain knowledge about Norway. Optimal results may require prompt tuning. The model is released under the Attribution-NonCommercial-ShareAlike 4.0 International license, restricting commercial use.