TheDrummer/Gemmasutra-Pro-27B-v1.1

TEXT GENERATIONPricing:Input $2.6 / Cached $0.13 / Output $2.6Concurrent Unit Cost:2Model Size:27BQuant:FP8Context Size:32kPublished:Jan 30, 2025License:otherArchitecture:Transformer0.0K Featherless Exclusive Cold

Gemmasutra-Pro-27B-v1.1 is a 27 billion parameter language model developed by TheDrummer, based on the Gemma architecture. This model incorporates modern fine-tuning techniques to enhance its performance. It is specifically tuned for conversational applications, utilizing the Gemma chat template for user and assistant interactions. The model is suitable for tasks requiring a refined Gemma-based LLM.

Loading preview...

Gemmasutra Pro 27B v1.1 Overview

Gemmasutra Pro 27B v1.1 is a 27 billion parameter language model developed by TheDrummer, building upon the Gemma architecture. This iteration, presented by BeaverAI, integrates contemporary fine-tuning methodologies to optimize its capabilities. The model is designed to leverage the Gemma chat template, supporting distinct user and assistant roles for conversational AI applications.

Key Capabilities

  • Gemma Architecture: Built on the Gemma foundation, indicating a focus on efficiency and performance within that family.
  • Modern Fine-tuning: Utilizes advanced techniques to enhance its base Gemma performance.
  • Conversational Support: Explicitly supports the Gemma chat template, making it suitable for dialogue-based interactions.

Good For

  • Chat Applications: Ideal for implementing conversational agents that require clear distinction between user and assistant prompts.
  • Gemma-based Projects: Developers already working with Gemma models may find this a refined alternative for their applications.
  • Exploration of Fine-tuned Gemma: Useful for researchers and developers interested in the impact of modern tuning techniques on the Gemma architecture.