Skip to content

EthenEthenEthen

Open Source Model Profile · TheTsar1209

gemma-carpskel-v0.1

gemma-carpskel-v0.1 is a Gemma 3 fine-tune from TheTsar1209 with about 12.19B parameters. According to the model card, it uses ChatML formatting with 24k context.

Publisher
TheTsar1209
Task
image-text-to-text
Model type
gemma3
License
apache-2.0
Library
transformers
Publication status
Accepted · not indexed

Model overview

gemma-carpskel-v0.1 is published by TheTsar1209 as an image-text-to-text model. The captured configuration identifies Gemma3ForConditionalGeneration with model type gemma3, and Safetensors metadata reports 12,187,325,040 parameters. According to the model card, it was continuously pretrained with Unsloth using ChatML with 24k context and finetuned from unsloth/gemma-3-12b-it-unsloth-bnb-4bit.

Recorded capabilities

ChatML formatting

According to the model card, the model was trained using Unsloth continuous pretraining with the ChatML format.

24k context claim

According to the model card, training used 24k context.

Documented Gemma 3 source

According to the model card, it was finetuned from unsloth/gemma-3-12b-it-unsloth-bnb-4bit and trained 2x faster with Unsloth and Hugging Face's TRL library.

Use cases in the source record

  • ChatML-formatted image-text-to-text generation workflows documented in the model card.
  • Conversational inference workflows consistent with the recorded conversational tags and the snapshot conversational provider listing.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • The 24k context value is a publisher model-card claim and was not independently verified.
  • Provider state is historical snapshot data and should be refreshed before being presented as current.

Source and provenance

Source: TheTsar1209/gemma-carpskel-v0.1

Captured: Unknown. Processed: 2026-09-07T19:35:52.457297+00:00.

A Fishy Model This model was trained using Unsloth's continuous pretraining with the ChatML format with 24k context. Uploaded model Developed by: TheTsar1209 License: apache-2.0 Finetuned from model : unsloth/gemma-3-12b-it-unsloth-bnb-4bit This gemma3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

F001F002F003F004F005F006F007F009F010F011F012