Advanced RoBerta and DistillBert Based Abstract Based Sentiment Analyzer. Ensemble Architecture
-
Updated
Jan 31, 2025 - Python
#
roberta-base
Here are 13 public repositories matching this topic...
Fine-tuning RoBERTa sentiment analysis model on tweets about the Coachella 2015 music festival lineup
-
Updated
Jun 8, 2025 - Jupyter Notebook
RoBERTa-base fine-tuned on the LIAR dataset for binary fake-news detection — 64.5% accuracy, 0.635 macro-F1, beating a TF-IDF + LogReg baseline (0.603). Includes class-weighted training, calibration analysis (ECE 0.042), per-class error breakdown, threshold selection, ONNX export, and a live Spaces demo. Reproducible from one Colab notebook.
machine-learning transformers pytorch fact-checking model-evaluation machine-learning-models fine-tuning onnx roberta liar-dataset transformers-models onnx-runtime roberta-model model-evaluation-metrics roberta-tokenizer fine-tuning-llm roberta-fine-tuning roberta-base roberta-sentiment-analysis fact-checking-nlp
-
Updated
Oct 22, 2026
A real-time, multilingual (English and Nepali) hate speech and profanity detection system for virtual meetings and classrooms, powered by XLM-RoBERTa and OpenAI Whisper.
-
Updated
Jun 14, 2026 - Jupyter Notebook
Mitigating a language model's over-confidence with NLI predictions on Multi-NLI hypotheses with random word order using PAWS (paraphrase) and Winogrande (anaphora).
language-model natural-language-inference classification-model paws nli roberta huggingface mnli-dataset winogrande roberta-base
-
Updated
May 28, 2024 - Jupyter Notebook
This repository contains the code, model configurations, and report for fine-tuning a roberta-base model using Low-Rank Adaptation (LoRA)- a Parameter-Efficient Fine-Tuning (PEFT) method - on the AG News classification task. The goal was to achieve high test accuracy while keeping trainable parameters under 1 million.
machine-learning performance deep-neural-networks deep-learning machine-learning-algorithms lora peft ag-news-dataset roberta-model roberta-base peft-fine-tuning-llm
-
Updated
Apr 22, 2025 - Jupyter Notebook
Detect and analyze resource leaks in Android apps using method signature matching and NLP-based similarity detection.
-
Updated
Jun 2, 2025 - Python
Leveraging logistic regression, XGBoost, LSTM, and the RoBERTa-base transformers from hugging face to detect fake news in web-hosted articles.
docker tensorflow torch xgboost logistic-regression transfer-learning lime beautifulsoup4 spacy-nlp fastapi streamlit-webapp roberta-base
-
Updated
Dec 30, 2025 - Jupyter Notebook
End2end Low-Rank Adaptation (LoRA) fine-tuning of RoBERTa on the TweetEval emoji dataset with CLI tools, Weights & Biases logging, and a Gradio demo.
pytorch lora gradio fine-tuning huggingface huggingface-transformers huggingface-spaces roberta-base tweet-eval
-
Updated
Jul 21, 2025 - Jupyter Notebook
Emoji Prediction from Text app demo
-
Updated
Jun 19, 2026 - Jupyter Notebook
Python pipeline for a peer-reviewed JAAER (2025) study on pilot emotions: a recursive scraper collected 1,130,530 posts from Airline Pilot Central Forums, then GPU-accelerated RoBERTa (GoEmotions) scored each on 28 emotions to compare passenger, cargo, and military pilots.
nlp natural-language-processing emotion-analysis roberta aviation-data roberta-model roberta-base pilot-burnout online-discourse aviation-psychology
-
Updated
Sep 17, 2026 - Python
SpaceY - Astronomical NLP with Encoder Transformers
-
Updated
Oct 25, 2025 - Python
This repository contains code for benchmarking ModernBERT, RoBERTa, and OPT-350m on multi-class emotion classification using 8-bit quantization, backbone freezing, and LoRA-based PEFT.
scikit-learn python3 pytorch scipy lora quantization emotion-analysis plotly-express huggingface-transformers int8-quantization supervised-finetuning llm-inference llm-fine-tuning roberta-base peft-fine-tuning-llm torchao modernbert facebook-opt cochrans-q-test
-
Updated
Oct 19, 2026 - Python
Add this topic to your repo
To associate your repository with the roberta-base topic, visit your repo's landing page and select "manage topics."