yang-ki/army_model_gemma2b

TEXT GENERATIONConcurrency Cost:1Model Size:2.5BQuant:BF16Ctx Length:8kPublished:Apr 15, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

yang-ki/army_model_gemma2b is a 2.5 billion parameter causal language model developed by yang-ki, based on Google's Gemma-2b architecture. This model is fine-tuned on the yang-ki/army_sample dataset, specifically optimized for Korean language tasks. With a context length of 8192 tokens, it is designed for text generation and demonstrates capabilities in accuracy metrics within its specialized domain.

Loading preview...

Overview

yang-ki/army_model_gemma2b is a 2.5 billion parameter language model built upon the robust Google Gemma-2b architecture. Developed by yang-ki, this model has been specifically fine-tuned using the yang-ki/army_sample dataset, indicating a specialization in a particular domain or task related to this dataset. It supports a substantial context length of 8192 tokens, allowing for processing and generating longer sequences of text.

Key Capabilities

  • Korean Language Focus: The model's training on a Korean dataset (yang-ki/army_sample) suggests strong performance and understanding in the Korean language.
  • Text Generation: As a causal language model, its primary function is text generation, suitable for various natural language processing tasks.
  • Gemma-2b Base: Leverages the foundational strengths and efficiency of the Gemma-2b model from Google.

Good For

  • Applications requiring text generation in Korean.
  • Research and development within the specific domain covered by the yang-ki/army_sample dataset.
  • Tasks where a balance between model size (2.5B parameters) and performance in a specialized Korean context is desired.