Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string
RB Residual Encoder — E5-small-v2 LoRA adapter
A representative LoRA adapter from Cross-Modal Residual Boosting (RB), a text-tabular learning method (NLP Course 097215 final project, Technion).
The adapter is a residual encoder: E5-small-v2 fine-tuned (LoRA, rank 16, layers 9–11) to predict the residuals of a tabular CatBoost baseline rather than the target directly, so the text representation is complementary by construction to the tabular features.
This adapter was trained on the MulTaBench MUL_TEXT_PRODUCT_SENTIMENT dataset,
fold 0. Usage (inference, no training) is documented in the project repository.
- Downloads last month
- 14
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for NoamBenzimra/rb-e5-residual-adapter
Base model
intfloat/e5-small-v2