vicgalle
/

configurable-preference-mistral-nemo-12b

Text Generation

Model card Files Files and versions Community

This is a LoRA adapter for unsloth/mistral-nemo-instruct-2407-bnb-4bit and was trained using the code and dataset described in the paper Configurable Preference Tuning with Rubric-Guided Synthetic Data.

The 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

Dataset used to train vicgalle/configurable-preference-mistral-nemo-12b

Collection including vicgalle/configurable-preference-mistral-nemo-12b

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 26 days ago • 1