SakitsunaAI/SlactusAIAstra
TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.2BQuant:BF16Context Size:32kPublished:Sep 2, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
SlactusAIAstra is a 1.2 billion parameter language model developed by SakitsunaAI, fine-tuned from unsloth/LFM2.5-1.2B-Instruct. This model was trained using Unsloth, enabling faster fine-tuning. It is designed for general language tasks, leveraging its efficient training methodology.
Loading preview...
SakitsunaAI/SlactusAIAstra Overview
SlactusAIAstra is a 1.2 billion parameter language model developed by SakitsunaAI. It is fine-tuned from the unsloth/LFM2.5-1.2B-Instruct base model, indicating its foundation in an existing instruction-tuned architecture.
Key Characteristics
- Efficient Training: This model was fine-tuned with Unsloth, a library known for accelerating the training process of large language models, achieving approximately 2x faster training speeds.
- Parameter Count: With 1.2 billion parameters, it offers a balance between performance and computational efficiency, suitable for various applications.
- License: The model is released under the Apache-2.0 license, allowing for broad use and distribution.
Potential Use Cases
- Applications requiring a compact yet capable language model.
- Scenarios where faster fine-tuning is a significant advantage.
- General instruction-following tasks, given its base model's instruction-tuned nature.