A LoRA fine-tuned version of Qwen3.5-9B using no-think tempalte now specialized in CTL2 (Clover Transformation Language 2) — the domain-specific language used for data transformations in CloverDX ETL pipelines.

This model assists developers writing CTL2 transformation code inside CloverDX. It can generate correct CTL2 expressions and transformation logic, explain built-in functions, help with component binding patterns, and answer questions about the language. Can also validate CTL code and produce findings in structured/formatted way.

Trained first on ~10k SFT examples, then ~1k DPO.

Downloads last month
1
Safetensors
Model size
9B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for dpavlis/Qwen3.5-9B-CTL

Finetuned
Qwen/Qwen3.5-9B
Finetuned
(482)
this model

Dataset used to train dpavlis/Qwen3.5-9B-CTL