davanstrien/qwen35-4b-iconclass-codesonly-poc2

VISIONConcurrent Unit Cost:1Model Size:4.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 5, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The davanstrien/qwen35-4b-iconclass-codesonly-poc2 is a 4.5 billion parameter Qwen3.5 model, finetuned by davanstrien. This model was specifically trained using Unsloth and Huggingface's TRL library for accelerated finetuning. It is a continuation of the davanstrien/qwen35-4b-iconclass-sft-brillfull model, focusing on specialized applications related to Iconclass codes.

Loading preview...

Model Overview

The davanstrien/qwen35-4b-iconclass-codesonly-poc2 is a 4.5 billion parameter Qwen3.5 model, developed by davanstrien. It is a finetuned iteration of the davanstrien/qwen35-4b-iconclass-sft-brillfull model, indicating a specialized focus building upon its predecessor.

Key Characteristics

  • Architecture: Based on the Qwen3.5 model family.
  • Parameter Count: 4.5 billion parameters.
  • Finetuning Method: This model was finetuned using Unsloth and Huggingface's TRL library, which enabled a 2x faster training process.
  • Origin: It is a direct finetune from davanstrien/qwen35-4b-iconclass-sft-brillfull, suggesting a continued specialization in Iconclass-related tasks.

Potential Use Cases

Given its finetuning origin and name, this model is likely optimized for tasks involving:

  • Processing or generating content related to Iconclass codes.
  • Applications requiring specialized knowledge within the Iconclass domain.

Licensing

The model is released under the Apache-2.0 license.

Finetunes
1 models