shuology/brooke-beta-02

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:May 29, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

shuology/brooke-beta-02 is a 7 billion parameter instruction-tuned causal language model developed by shuology. It is finetuned from unsloth/mistral-7b-instruct-v0.3-bnb-4bit and was trained using Unsloth and Huggingface's TRL library for faster finetuning. This model is optimized for general instruction-following tasks, leveraging the Mistral architecture.

Loading preview...

Model Overview

shuology/brooke-beta-02 is a 7 billion parameter instruction-tuned language model, developed by shuology. It is built upon the Mistral architecture, specifically finetuned from unsloth/mistral-7b-instruct-v0.3-bnb-4bit. The finetuning process utilized Unsloth and Huggingface's TRL library, which enabled a significantly faster training time.

Key Characteristics

  • Base Model: Finetuned from Mistral-7B-Instruct-v0.3, providing a strong foundation for instruction-following.
  • Efficient Training: Leverages Unsloth for 2x faster finetuning, making it a practical choice for developers seeking efficient model adaptation.
  • Parameter Count: Features 7 billion parameters, balancing performance with computational efficiency.

Use Cases

This model is suitable for a variety of general instruction-following tasks, benefiting from its Mistral lineage and efficient finetuning. Developers looking for a capable 7B model that was trained with performance optimizations will find this model particularly useful.