kortivai/shiva-alpha-base-surgery-v2

TEXT GENERATIONConcurrent Unit Cost:1Model Size:2.5BQuant:BF16Context Size:8kPublished:Jul 8, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The kortivai/shiva-alpha-base-surgery-v2 is a 2.5 billion parameter language model developed by kortivai, fine-tuned from Google's Gemma-2B. This model was trained using Unsloth, enabling 2x faster training. It is designed for general language tasks, leveraging its efficient training methodology.

Loading preview...

Model Overview

The kortivai/shiva-alpha-base-surgery-v2 is a 2.5 billion parameter language model developed by kortivai. It is fine-tuned from the google/gemma-2b base model, indicating its foundation in Google's Gemma architecture. A notable aspect of its development is the use of Unsloth, which facilitated a 2x speedup in its training process.

Key Characteristics

  • Base Model: Fine-tuned from google/gemma-2b.
  • Parameter Count: 2.5 billion parameters.
  • Context Length: Supports an 8192-token context window.
  • Training Efficiency: Leveraged Unsloth for accelerated training.
  • License: Released under the Apache-2.0 license.

Potential Use Cases

This model is suitable for applications requiring a compact yet capable language model, especially where efficient deployment and inference are critical. Its Gemma-2B foundation suggests applicability in various general-purpose natural language processing tasks, including text generation, summarization, and question answering, within its 8192-token context limit.