zlyngkhoi/txgemma-2b-trialbench-sft

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2.6BQuant:BF16Context Size:8kPublished:Aug 18, 2026Architecture:Transformer Featherless Exclusive Cold

The zlyngkhoi/txgemma-2b-trialbench-sft model is a 2.6 billion parameter language model fine-tuned from google/txgemma-2b-predict using the SFT algorithm and TRL backend. Developed by zlyngkhoi, this model leverages the Aligntune framework, which supports various open-source models and algorithms. It is designed for general language generation tasks, offering a compact yet capable solution for developers.

Loading preview...

Model Overview

The txgemma-2b-trialbench-sft is a 2.6 billion parameter language model developed by zlyngkhoi. It is fine-tuned from the google/txgemma-2b-predict base model using the Supervised Fine-Tuning (SFT) algorithm, implemented with the TRL backend. This model's development utilized the Aligntune framework, which is designed to support various open-source models, algorithms, and backends.

Key Characteristics

  • Base Model: Fine-tuned from google/txgemma-2b-predict.
  • Parameter Count: 2.6 billion parameters, offering a balance between performance and computational efficiency.
  • Fine-tuning Method: Employs the SFT (Supervised Fine-Tuning) algorithm.
  • Development Framework: Built with Aligntune, providing flexibility in model development.

Usage

This model is suitable for integration into applications requiring a compact language model for various text generation and understanding tasks. Its architecture and fine-tuning approach make it a practical choice for developers looking for a readily available, pre-trained model.