gigi181091/qwen3-vl-8b-instruct-unsloth-bnb-4bit-vi-handwriting-finetune

VISIONPricing:Input $0.727 / Output $5.405Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Nov 2, 2025License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The gigi181091/qwen3-vl-8b-instruct-unsloth-bnb-4bit-vi-handwriting-finetune is an 8 billion parameter Qwen3-VL instruction-tuned model, developed by gigi181091. It was fine-tuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. This model is specifically designed for Vietnamese handwriting tasks, leveraging its vision capabilities and instruction-following fine-tuning.

Loading preview...

Model Overview

This model, developed by gigi181091, is a fine-tuned version of the Qwen3-VL 8B Instruct model. It leverages the Qwen3-VL architecture, which is known for its multimodal capabilities, specifically vision and language understanding.

Key Characteristics

  • Base Model: Fine-tuned from unsloth/qwen3-vl-8b-instruct-unsloth-bnb-4bit.
  • Parameter Count: 8 billion parameters.
  • Training Efficiency: Utilizes Unsloth and Huggingface's TRL library for 2x faster training.
  • Multimodal: Inherits the vision-language capabilities of the Qwen3-VL family.

Primary Use Case

This specific fine-tune is optimized for Vietnamese handwriting tasks, suggesting its application in scenarios requiring recognition or processing of handwritten Vietnamese text. Its instruction-following nature makes it suitable for tasks where specific instructions guide the interpretation of visual input.