gemma4-12b-biblical-qlora is an open-weight model from Serialhex. Its published files total 296.0 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—
Weights263.8 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
- Publisher
- Serialhex
- Task
- Not stated by the source
- Modality
- Other
- Library
- transformers
- Parameters
- Not stated by the source
- Languages
- trl, sft
- Revision
- 716f3cae44ae3eb32676694a412f21a570b5b2a5
- First published
- 2026-10-08
- Last updated
- 2026-10-10
Files and Weights
9 files, 296.0 MB in total. The weights are 2 files totalling 263.8 MB in bin, safetensors.
Weights2 files · 263.8 MB
Configuration2 files · 2.6 KB
Tokenizer2 files · 32.2 MB
Documentation1 file · 1.5 KB
Other1 file · 18.7 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_model.safetensors | Weights | 263.8 MB | 3fcc151981d4 |
| training_args.bin | Weights | 5.8 KB | f6931f3ef40a |
| adapter_config.json | Configuration | 1.2 KB | — |
| processor_config.json | Configuration | 1.4 KB | — |
| README.md | Documentation | 1.5 KB | — |
| chat_template.jinja | Other | 18.7 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 32.2 MB | a2619fe11b50 |
| tokenizer_config.json | Tokenizer | 3.7 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 263.8 MB
Download from Serialhex
Released by Serialhex through its official repository on Hugging Face.
Built From
- Derived from google/gemma-4-12B-it
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 263.8 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.