Recorded Gemma 3 12B base
Hub tags and the model card record unsloth/gemma-3-12b-it-unsloth-bnb-4bit as the fine-tune source.
Open Source Model Profile · berkaygkv54
gemma3-12b-tolkien
gemma3-12b-tolkien is a 12.19B-parameter berkaygkv54 Gemma 3 fine-tune for image-text-to-text work. Its model card records an Unsloth Gemma 3 12B instruction base.
- Publisher
- berkaygkv54
- Task
- image-text-to-text
- Model type
- gemma3
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
gemma3-12b-tolkien is published by berkaygkv54 as an image-text-to-text fine-tune. 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 finetuned from unsloth/gemma-3-12b-it-unsloth-bnb-4bit.
Recorded capabilities
Captured 12.19B configuration
The captured configuration identifies Gemma3ForConditionalGeneration with model type gemma3 and Safetensors metadata reports 12,187,325,040 parameters.
Unsloth and TRL stack
According to the model card, the model trained with Unsloth and Hugging Face TRL library tooling.
Use cases in the source record
- Conversational image-text-to-text experiments using the Transformers stack, within the limits of the sparse documentation.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No context-window value was extracted from this record.
- No dataset details were extracted from this record.
- Provider state is historical snapshot data and should be refreshed before being presented as current.
Source and provenance
Source: berkaygkv54/gemma3-12b-tolkien
Captured: Unknown. Processed: 2026-09-07T19:35:54.637143+00:00.
Uploaded finetuned model Developed by: berkaygkv54 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.
F001F002F003F004F005F006F007F008F009F010F011