nlp

Runtime detector for reward hacking and misalignment in LLM agents (89.7% F1 on 5,391 trajectories).

Build LLM-enabled FastAPI applications without build configuration.

Comparing Selective Masking Methods for Depression Detection in Social Media

Indonesian news summarization with IndoBART / mT5 (headline + paragraph summary).

QDrant-NLP

No longer maintained, please see the TypeScript client

Chinese-Multimodal-Sentiment-Analysis is an innovative project that integrates advanced deep learning techniques to analyze sentiments in Chinese language data. Utilizing a sophisticated blend of textual, audio, and visual modalities, this project offers a comprehensive approach to understanding and interpreting complex emotional expressions.

Batch LLM Inference with Ray Data LLM: From Simple to Advanced

Generate novel text - novel finetuned from skt KoGPT2 base v2 - 한국어

An automated solution for fact-checking using available claims and fake-news datasets to fine-tune state-of-the-art language models published recently for NLP tasks (BERT, RoBERTa, XLNet, ConvBERT...) in order to classify unseen claims.

🤖 Deep Catalan: Bring closer the Catalan Language to Deep Learning using ULMFit.

In the context of Morocco (Darija), sentiment analysis can be an invaluable asset for businesses and organizations looking to better understand the satisfaction of their customers. We will fine-tune a model for Darija

Earth observations, especially satellite data, have produced a wealth of methods and results in meeting global challenges, often presented in unstructured texts such as papers or reports. Accurate extraction of satellite and instrument entities from these unstructured texts can help to link and reuse Earth observation resources.

CatIss is an intelligent tool for automatic categorization of issue reports based on the RoBERTa model.

Fine-tune a local LLM on your own chat history to mimic how you write — an AI doppelganger / digital-twin toolkit built on LLaMA-Factory (LoRA SFT).

Blenderbot

AI-powered emotion detection & personalized recommendations using NLP and machine learning

Code and dataset for paper - Application of Deep Learning in Generating Structured Radiology Reports: A Transformer-Based Technique

Wrapper for stable version of RoBERTa language models

Engineered an advanced deep learning model to automate the classification of financial documents, including Balance Sheets, Cash Flow and Income Statements using Bidirectional LSTM and TensorFlow. The model achieved an impressive accuracy of 96.2%, enhancing efficiency and reducing errors in document management for the finance and banking sectors.