Downloads · 30 days
4
10% of all-time downloads
dataset-templater-lora
ziksy/dataset-templater-lora
dataset-templater-lora is a machine learning model from ziksy. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Qwen2.5-14B-Instruct LoRA for dataset schema templating.
All-time downloads
39
Public
Repo size
413 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors275 MB · 66%
At a glance
- Access
- Public
- Created
- Apr 18, 2026
- Updated
- Apr 18, 2026
- SHA
- e939870c
Model card
From the Hugging Face model README
dataset-templater-lora
Qwen2.5-14B-Instruct LoRA for dataset schema templating.
Eval (190-item holdout)
- shape_match: 25.3%% -> 68.4%% (+43pp)
- column_sanity: 52.1%% -> 91.6%% (+40pp)
- valid_json: 100%% (both)
Trained on 2000 synthesized schema-mapping examples across 13 families including adversarial legal-structured datasets and hard-negative refusal cases.
Use
Hot-load via llama.cpp /lora-adapters/load. See adapters/qwen2514binstruct/ for GGUF and safetensors.
- Created
- Apr 18, 2026
- Updated
- Apr 18, 2026