mr-muhammed/Celine

TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 14, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

Celine is a 7.6 billion parameter Qwen2-based instruction-tuned causal language model developed by mr-muhammed. This model was fine-tuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for general instruction-following tasks, leveraging its efficient training methodology.

Loading preview...

Model Overview

Celine is a 7.6 billion parameter instruction-tuned language model developed by mr-muhammed. It is based on the Qwen2 architecture and was fine-tuned from unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit.

Key Characteristics

  • Efficient Training: Celine was trained 2x faster by utilizing Unsloth and Huggingface's TRL library. This indicates an optimization for resource-efficient fine-tuning processes.
  • Base Model: Built upon the Qwen2.5-7B-Instruct model, suggesting strong general language understanding and generation capabilities.
  • Context Length: Supports a context length of 32768 tokens, allowing for processing and generating longer sequences of text.

Use Cases

Celine is suitable for a variety of instruction-following tasks, benefiting from its Qwen2 base and optimized fine-tuning. Its efficient training process makes it a good candidate for developers looking for performant models that can be quickly adapted or deployed.