jekunz/Gemma-3-1B-it-sv-SmolTalk

TEXT GENERATIONConcurrency Cost:1Model Size:1BQuant:BF16Ctx Length:32kPublished:Apr 24, 2026Architecture:Transformer Cold

jekunz/Gemma-3-1B-it-sv-SmolTalk is a 1 billion parameter instruction-tuned causal language model, fine-tuned by jekunz from Google's Gemma-3-1B-it base model. This model specializes in Swedish language understanding and generation, leveraging its fine-tuning for conversational tasks. It is optimized for applications requiring efficient and accurate responses in Swedish, making it suitable for chatbots and localized content generation.

Loading preview...

Overview

jekunz/Gemma-3-1B-it-sv-SmolTalk is a 1 billion parameter instruction-tuned language model, derived from Google's Gemma-3-1B-it. This model has been specifically fine-tuned using the TRL library to enhance its performance, particularly for Swedish language tasks.

Key Capabilities

  • Instruction Following: Designed to understand and execute instructions effectively.
  • Swedish Language Proficiency: Optimized for generating and comprehending text in Swedish.
  • Conversational AI: Suitable for dialogue-based applications due to its instruction-tuned nature.

Training Details

The model was trained using Supervised Fine-Tuning (SFT) with the TRL framework (version 0.25.1). It leverages the robust architecture of the Gemma-3-1B-it base model, adapting it for specialized use cases through targeted fine-tuning.

Good For

  • Developing chatbots or virtual assistants that interact in Swedish.
  • Generating localized content or responses for Swedish-speaking audiences.
  • Applications requiring a compact yet capable model for instruction-based tasks in Swedish.