A community hub for collecting and sharing real-world issues with LLMs and other models to help improve their capabilities.

This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks" [ICLR25]

A PyTorch Native LLM Training Framework

Salesforce open-source LLMs with 8k sequence length.

Unified Controllable Visual Generation Model

A deep learning library for identifying keyphrases from text

CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.

ACTER is a manually annotated dataset for term extraction, covering 3 languages (English, French, and Dutch), and 4 domains (corruption, dressage, heart failure, and wind energy).

Automatically generate your résumé and various cover letters from YAML files.

Code to obtain the PMC-SA. A dataset for the summarization of scientific articles.

Everything you need to know for a Software Engineering interview

BART summarization tool

Large, curated set of benchmark datasets for evaluating automatic keyphrase extraction algorithms.

🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

AutoPhrase: Automated Phrase Mining from Massive Text Corpora

Plot the vector graph of attention based text visualisation

Keyphrase Generation

Python Keyphrase Extraction module

An open-source NLP research library, built on PyTorch.

A collection of corpora for named entity recognition (NER) and entity recognition tasks. These annotated datasets cover a variety of languages, domains and entity types.

Full Python implementation of the ROUGE metric, producing same results as in the official perl implementation.

A Python wrapper for the ROUGE summarization evaluation package

Unsupervised Language Modeling at scale for robust sentiment classification

PyTorch original implementation of Cross-lingual Language Model Pretraining.

Facebook AI Research Sequence-to-Sequence Toolkit