Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · summykai

gemma3-27b-abliterated-dpo

gemma3-27b-abliterated-dpo is a 27.43B-parameter Gemma 3 fine-tune from summykai. According to the model card, it was fine-tuned from mlabonne/gemma-3-27b-it-abliterated.

Publisher
summykai
Task
image-text-to-text
Model type
gemma3
License
gemma
Library
transformers
Publication status
Accepted · not indexed

Model overview

gemma3-27b-abliterated-dpo is published by summykai as a Gemma 3 image-text-to-text fine-tune. The captured configuration identifies Gemma3ForConditionalGeneration with model type gemma3, and Safetensors metadata reports 27,432,406,640 parameters. According to the model card, it was fine-tuned from mlabonne/gemma-3-27b-it-abliterated.

Recorded capabilities

DPO fine-tune lineage

According to the model card, this is an uploaded fine-tuned model developed by Summykai from mlabonne/gemma-3-27b-it-abliterated.

Unsloth and TRL training stack

According to the model card, the Gemma 3 model trained with Unsloth and Hugging Face's TRL library, and hub tags record an unsloth association.

Captured 27.43B Transformers weights

Safetensors metadata reports 27,432,406,640 parameters, and the hub record lists Transformers support.

ORPO-DPO mix dataset association

Hub tags record a dataset association with mlabonne/orpo-dpo-mix-40k.

Use cases in the source record

  • Conversational text-and-image-in generation experiments on a 27B-scale Gemma 3 DPO fine-tune.
  • Preference-tuning research building on the publisher-documented Unsloth and TRL workflow and DPO-mix dataset association.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • No context-window value was extracted from this record.
  • Derivation and tooling detail comes from a brief publisher card and was not independently verified by Ethen.
  • Provider state is historical snapshot data and should be refreshed before being presented as current.

Source and provenance

Source: summykai/gemma3-27b-abliterated-dpo

Captured: Unknown. Processed: 2026-09-07T19:35:31.196805+00:00.

Uploaded finetuned model Developed by: Summykai License: apache-2.0 Finetuned from model : mlabonne/gemma-3-27b-it-abliterated This gemma3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

F001F002F003F004F005F006F007F008F009F010F011