timpal0l/gpt-sw3-6.7b-v2-instruct

TEXT GENERATIONPricing:Input $0.4 / Cached $0.02 / Output $0.8Concurrent Unit Cost:1Model Size:7.1BQuant:FP8Context Size:2kPublished:Apr 18, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

GPT-Sw3 6.7B v2 Instruct is a 7.1 billion parameter decoder-only transformer language model developed by AI Sweden in collaboration with RISE and WASP WARA. It is instruction-tuned and pretrained on a 320 billion token dataset comprising Swedish, Norwegian, Danish, Icelandic, English, and programming code. This model is designed for generating coherent text in five languages and four programming languages, and can perform various text tasks through instruction-based generation.

Loading preview...

Model Overview

GPT-Sw3 6.7B v2 Instruct is a 7.1 billion parameter instruction-tuned language model developed by AI Sweden, RISE, and WASP WARA. It is part of the GPT-Sw3 collection, which focuses on Nordic languages. The model was pretrained using a causal language modeling objective with the NeMo Megatron GPT implementation.

Key Capabilities

  • Multilingual Text Generation: Capable of generating coherent text in Swedish, Norwegian, Danish, Icelandic, and English.
  • Code Generation: Supports text generation in four programming languages.
  • Instruction Following: Fine-tuned on instruction data (both chat and raw text formats) to perform diverse text tasks not explicitly trained for, by casting them as text generation problems.
  • Extensive Training Data: Pretrained on a substantial 320 billion token dataset, including a significant portion of Nordic languages and programming code.

Intended Use Cases

This model is primarily intended for research and evaluation of Large Language Models, particularly for the Nordic languages. It is suitable for:

  • Generating text in Swedish, Norwegian, Danish, Icelandic, and English.
  • Performing various instruction-based text tasks.
  • Code generation.

Limitations

Like other large language models, GPT-Sw3 6.7B v2 Instruct has limitations regarding bias, safety, generation diversity, and hallucination. It may overrepresent certain viewpoints, contain stereotypes, or generate inappropriate content. Users should be aware of these potential issues and consider the modified RAIL license for usage guidelines.

Finetunes
3 models