L1nus/gemma4-26b-a4b-kiid-r16-allexperts
L1nus/gemma4-26b-a4b-kiid-r16-allexperts is a 26 billion parameter language model, fine-tuned from unsloth/gemma-4-26b-a4b-it. This model was trained using Supervised Fine-Tuning (SFT) with the TRL framework. It is designed for general text generation tasks, leveraging its large parameter count and fine-tuning for robust performance.
Loading preview...
Model Overview
L1nus/gemma4-26b-a4b-kiid-r16-allexperts is a 26 billion parameter language model, fine-tuned from the unsloth/gemma-4-26b-a4b-it base model. This model was developed using the TRL (Transformer Reinforcement Learning) framework, specifically employing Supervised Fine-Tuning (SFT) for its training procedure.
Key Characteristics
- Base Model: Fine-tuned from
unsloth/gemma-4-26b-a4b-it. - Training Method: Utilizes Supervised Fine-Tuning (SFT).
- Frameworks: Trained with TRL (version 0.24.0), Transformers (version 5.5.0), Pytorch (version 2.10.0+cu128), Datasets (version 4.3.0), and Tokenizers (version 0.22.2).
Intended Use
This model is suitable for various text generation tasks, as demonstrated by the quick start example involving a conversational question. Its fine-tuned nature suggests an ability to produce coherent and contextually relevant responses.