Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · aashish093

qwen3-vl-4b-scheme-extract

qwen3-vl-4b-scheme-extract is a 4.44B-parameter Qwen3-VL image-text-to-text fine-tune from aashish093. Its model card identifies unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit as the source model.

Publisher
aashish093
Task
image-text-to-text
Model type
qwen3_vl
License
apache-2.0
Library
transformers
Publication status
Accepted · not indexed

Model overview

qwen3-vl-4b-scheme-extract is published by aashish093 as an image-text-to-text model. The captured configuration identifies Qwen3VLForConditionalGeneration and Safetensors metadata reports 4,437,815,808 parameters. According to the model card, it was developed by aashish093 and fine-tuned from unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit, with card data recording apache-2.0.

Recorded capabilities

Qwen3-VL fine-tune record

According to the model card, this qwen3_vl model was fine-tuned from unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit, matching hub tags recording the same base.

Vision-language architecture

Captured configuration records Qwen3VLForConditionalGeneration with model type qwen3_vl and Transformers support.

Apache-2.0 record

Card data records apache-2.0, and the model card states Apache-2.0 licensing.

Use cases in the source record

  • Image-text-to-text generation workflows using the Qwen3-VL Transformers setup suggested by the recorded pipeline tag and library.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • No context-window, resolution, or image-conditioning detail was extracted from this record.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: aashish093/qwen3-vl-4b-scheme-extract

Captured: Unknown. Processed: 2026-09-07T19:35:53.440933+00:00.

Uploaded finetuned model Developed by: aashish093 License: apache-2.0 Finetuned from model : unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit This qwen3_vl model was trained 2x faster with Unsloth and Huggingface's TRL library.

F001F002F003F004F005F006F007F008F009F010F011