vicgalle
/

configurable-preference-qwen3-4b

Text Generation

Model card Files Files and versions Community

This repository contains the CPT-tuned model described in Configurable Preference Tuning with Rubric-Guided Synthetic Data.

The training code is available at https://github.com/vicgalle/configurable-preference-tuning.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

Text Generation

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for vicgalle/configurable-preference-qwen3-4b

Base model

Qwen/Qwen3-4B-Base

Finetuned

Quantized

unsloth/Qwen3-4B-unsloth-bnb-4bit

Finetuned

(68)

this model

Dataset used to train vicgalle/configurable-preference-qwen3-4b

Collection including vicgalle/configurable-preference-qwen3-4b

Configurable Preference Tuning ⚙️📝

CPT uses rubric-guided synthetic data and DPO to enable LLMs to dynamically adjust behavior (e.g., writing style) at inference with system prompts • 7 items • Updated 30 days ago • 1