Skip to page content
SAVRN
Search Plan a project

Open-weight model

gemma4-12b-biblical-qlora-gt

by Serialhex serialhex/gemma4-12b-biblical-qlora-gt

gemma4-12b-biblical-qlora-gt is an open-weight model from Serialhex. Its published files total 163.6 MB.

This model is a fine-tuned version of google/gemma-4-12B-it. It has been trained using TRL. This model was trained with SFT.

Parameters—
Context—
Weights131.4 MB
License—
AccessOpen weights
Monthly Downloads—

Model Card

This model is a fine-tuned version of google/gemma-4-12B-it. It has been trained using TRL. This model was trained with SFT.

Excerpt from the card by Serialhex.

Identity and Version

Repository
serialhex/gemma4-12b-biblical-qlora-gt
Publisher
Serialhex
Task
Not stated by the source
Modality
Other
Library
transformers
Parameters
Not stated by the source
Languages
trl, sft
Revision
cba2382014dbc24e91d76875e8d12c9e7230e2bf
First published
2026-10-12
Last updated
2026-10-14

Files and Weights

9 files, 163.6 MB in total. The weights are 2 files totalling 131.4 MB in bin, safetensors.

Weights2 files · 131.4 MB
Configuration2 files · 3.1 KB
Tokenizer2 files · 32.2 MB
Documentation1 file · 1.5 KB
Other1 file · 18.7 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
adapter_model.safetensorsWeights131.4 MB a42bfd0c9c64
training_args.binWeights5.9 KB 4fcbf1216556
adapter_config.jsonConfiguration1.7 KB —
processor_config.jsonConfiguration1.4 KB —
README.mdDocumentation1.5 KB —
chat_template.jinjaOther18.7 KB —
.gitattributesRepository1.6 KB —
tokenizer.jsonTokenizer32.2 MB cc8d3a0ce364
tokenizer_config.jsonTokenizer3.7 KB —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
131.4 MB
Download from Serialhex

Released by Serialhex through its official repository on Hugging Face.

Built From

Memory Requirements

PrecisionWeights in memory
As published131.4 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.