ahmet-erman/cosmos-turkish-culture-veri_1-epoch_1000-checkpoint_420-loss_1.04

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:9BQuant:FP8Ctx Length:16kPublished:May 22, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

The ahmet-erman/cosmos-turkish-culture-veri_1-epoch_1000-checkpoint_420-loss_1.04 is a 9 billion parameter Gemma2 model, fine-tuned by ahmet-erman. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training speeds. It is designed for applications requiring a Turkish language model, building upon the ytu-ce-cosmos/Turkish-Gemma-9b-v0.1 base model.

Loading preview...

Model Overview

This model, developed by ahmet-erman, is a fine-tuned Gemma2 architecture with 9 billion parameters and a 16384 token context length. It is based on the ytu-ce-cosmos/Turkish-Gemma-9b-v0.1 model and was trained using a combination of Unsloth and Huggingface's TRL library.

Key Training Details

  • Base Model: ytu-ce-cosmos/Turkish-Gemma-9b-v0.1
  • Training Optimization: Utilized Unsloth for 2x faster fine-tuning.
  • Libraries Used: Huggingface's TRL library.

Potential Use Cases

This model is particularly suited for applications requiring a robust Turkish language understanding and generation, benefiting from its Gemma2 architecture and optimized training process. Its fine-tuned nature suggests specialization in areas related to Turkish culture, as implied by its name.