Open-weight model
gemma-text-to-sql-2026-09-18_20.49.16-finetune-QLORA
by Viktor Kovtun vkovtun/gemma-text-to-sql-2026-09-18_20.49.16-finetune-QLORA
gemma-text-to-sql-2026-09-18_20.49.16-finetune-QLORA is an open-weight model from Viktor Kovtun. Its published files total 1.6 GB.
This model is a fine-tuned version of google/gemma-4-E2B. It has been trained using TRL. This model was trained with SFT.
Model Card
This model is a fine-tuned version of google/gemma-4-E2B. It has been trained using TRL. This model was trained with SFT.
Excerpt from the card by Viktor Kovtun.
Identity and Version
- Repository
- vkovtun/gemma-text-to-sql-2026-09-18_20.49.16-finetune-QLORA
- Publisher
- Viktor Kovtun
- Task
- Not stated by the source
- Modality
- Other
- Library
- transformers
- Parameters
- Not stated by the source
- Languages
- trl, sft
- Revision
- 0e3bb101e576f311b64ecf96430b9dd71a921190
- First published
- 2026-09-18
- Last updated
- 2026-09-19
Files and Weights
10 files, 1.6 GB in total. The weights are 2 files totalling 1.6 GB in bin, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_model.safetensors | Weights | 1.6 GB | 062d305e6395 |
| training_args.bin | Weights | 5.8 KB | 2c4b722cdc46 |
| adapter_config.json | Configuration | 1.1 KB | — |
| processor_config.json | Configuration | 1.7 KB | — |
| README.md | Documentation | 1.7 KB | — |
| chat_template.jinja | Other | 18.6 KB | — |
| runs/Sep18_20-49-51_viktor-zbook/events.out.tfevents.1789757391.viktor-zbook.166539.0 | Other | 584.4 KB | 2df0969aba5e |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 32.2 MB | c2cf15ae878b |
| tokenizer_config.json | Tokenizer | 3.7 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 1.6 GB
Released by Viktor Kovtun through its official repository on Hugging Face.
Built From
- Derived from google/gemma-4-E2B
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.