chkab/gemma-2-2b-haddiyyisa-v2-merged
TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2.6BQuant:BF16Context Size:8kPublished:Oct 3, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
chkab/gemma-2-2b-haddiyyisa-v2-merged is a 2.6 billion parameter Gemma-2 model developed by chkab, fine-tuned from unsloth/gemma-2-2b-it-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster fine-tuning. It is designed for efficient deployment and applications requiring a compact yet capable language model.
Loading preview...
Overview
chkab/gemma-2-2b-haddiyyisa-v2-merged is a 2.6 billion parameter language model based on the Gemma-2 architecture. Developed by chkab, this model was fine-tuned from the unsloth/gemma-2-2b-it-bnb-4bit base model.
Key Capabilities
- Efficient Fine-tuning: This model was fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process compared to standard methods.
- Compact Size: With 2.6 billion parameters, it offers a balance between performance and computational efficiency, making it suitable for resource-constrained environments or applications requiring faster inference.
Good for
- Rapid Prototyping: The efficient fine-tuning process makes it ideal for developers looking to quickly adapt a capable language model to specific tasks.
- Edge Devices & Local Deployment: Its smaller parameter count allows for easier deployment on devices with limited memory or processing power.
- Applications requiring a Gemma-2 base: Leverages the underlying capabilities of the Gemma-2 architecture in a fine-tuned package.