kyoungsook70/dama-aibrain
VISIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:5.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 21, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
kyoungsook70/dama-aibrain is a 5.1 billion parameter instruction-tuned causal language model, finetuned from the Gemma-4-e2b-it architecture. Developed by kyoungsook70, this model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training speeds. It is designed for general instruction-following tasks, leveraging its efficient training methodology.
Loading preview...
Model Overview
kyoungsook70/dama-aibrain is a 5.1 billion parameter instruction-tuned language model, developed by kyoungsook70. It is finetuned from the unsloth/gemma-4-e2b-it-unsloth-bnb-4bit base model, indicating its foundation on the Gemma-4-e2b-it architecture.
Key Characteristics
- Efficient Training: This model was trained with Unsloth and Huggingface's TRL library, resulting in a 2x faster training process compared to standard methods.
- Instruction-Tuned: As an instruction-tuned model, it is designed to follow user prompts and instructions effectively.
- Architecture: Based on the Gemma-4-e2b-it architecture, providing a robust foundation for its language capabilities.
Potential Use Cases
- General Instruction Following: Suitable for a wide range of tasks where the model needs to understand and execute instructions.
- Research into Efficient Finetuning: Can serve as a practical example for developers interested in applying Unsloth for faster model training.
This model is licensed under Apache-2.0.