d-s-b/gemma-270m-gsm8k
TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.3BQuant:BF16Context Size:32kPublished:Oct 30, 2025Architecture:Transformer Featherless Exclusive Cold
The d-s-b/gemma-270m-gsm8k model is a 0.3 billion parameter language model, fine-tuned from google/gemma-3-270m-it. This model was trained using the TRL library, focusing on specific tasks. Its small size and fine-tuned nature suggest optimization for efficient deployment in applications requiring focused language generation.
Loading preview...
Model Overview
The d-s-b/gemma-270m-gsm8k is a compact language model with 0.3 billion parameters, derived from the google/gemma-3-270m-it base model. It has undergone supervised fine-tuning (SFT) using the TRL library, indicating a specialization for particular tasks rather than broad general-purpose language generation.
Key Capabilities
- Fine-tuned Gemma Architecture: Built upon the Gemma-3-270m-it model, suggesting foundational capabilities in text generation and understanding.
- SFT Training: Optimized through Supervised Fine-Tuning, which typically enhances performance on specific datasets or instruction-following tasks.
- Efficient Deployment: With only 0.3 billion parameters, this model is suitable for environments where computational resources are limited, or faster inference is required.
Good For
- Specific Task Integration: Ideal for applications requiring a small, specialized language model that can be integrated efficiently.
- Resource-Constrained Environments: Its compact size makes it a good candidate for deployment on edge devices or in scenarios with limited GPU memory.
- Further Fine-tuning: Can serve as a strong base for additional fine-tuning on even more niche datasets due to its already specialized training.