Efficient and Scalable Estimation of Tool Representations in Vector Space

Finetuning the DeBERTa v3 model for the emotion recognition task

Detect or classify input sentences as grammatically correct or incorrect by fine-tuning pre-trained DeBERTa-v3 model

Official repository for the EMNLP 2024 paper "How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics"

Application for training the pretrained transformer model DeBERTaV3 on an Aspect Based Sentiment Analysis task

Real-time prompt injection firewall for LLM applications. Detects jailbreaks, prompt leaks, indirect injections, and adversarial prompts.

Finding the source code hidden in the text.

Educational workshop for NLP engineers. Fine-tuning DeBERTa-v3 for CEFR level prediction on serverless Modal GPUs.

Submodular Subset Selection for Long-Document Question Answering

Challenge to distinguish whether a sentence from a news article expresses the subjective view of the author behind it or presents an objective view on the covered topic

Backbone: 5 x DeBerta and Head: Rapids SVR

Real-time prompt injection defense at the edge. A zero-trust Chrome extension and local AI backend that intercepts cognitive threats before they reach your LLMs.

Tactical next-action + reasoning prediction on 348 football match contexts (Shipd Project Eris). 4-component ensemble with task-coupling: DeBERTa-v3-base / large, cross-encoder MCQ scorer, zero-shot NLI, and a three-pass Qwen3.5-35B-A3B-Int4 + Gemma-4-26B-A4B-it MoE fusion with PRM rerank. W&B-instrumented. Target combined ≥ 0.80

Explainable Aspect-Based Sentiment Analysis for Startup Employee Reviews using DeBERTa-v3 and SHAP.

Split-based Prompt Injection Detector

This repo details code for building a text classifier for predicting Bank Transaction categories. I finetune a base version of a DeBERTaV3 model purely on text data, as well as another version using a combination of text and non-text (e.g., categorical, datetime, etc.) data.

IELTS Automated Essay Scoring (AES) – Multi-Task DeBERTa-based Architecture

ViBERTa is a fine-tuned DeBERTa model for sentiment analysis of McDonald's customer reviews, classifying sentiments as positive, negative, or neutral.

TypeScript/Deno implementation of DeBERTa-Biaffine dependency parser using ONNX Runtime.