OpenNMT-py
This open-source framework, based on PyTorch, is designed for natural language processing tasks such as neural machine translation, language modeling, and summarization. The project is no longer actively supported, with developers being advised to switch to the new Eole project. The current version includes features such as LLM support, 4/8-bit quantization, LoRA adapters, and tensor parallelism.
OpenNMT · Translation & NLP
Common commercial products in this category: Google Translate, DeepL, Microsoft Translator
- You train models for neural machine translation and language modeling projects.
- You fine-tune major language models like Llama, Mistral and Falcon.
- You make an inference using low memory GPU 4-bit or 8-bit quantization.
- • Last update over 1 year ago
- • NeutralGitHub Issue
Abstractive Summarization Results
“Hey guys, looking at recent pull requests and issues, it looks like a common interest of contributors (On top of NMT obv) is Abstractive Summarization. Any suggestions of how to train a model that will get close results to recent papers on the CNN-Daily Mail Database? Any…”
- • NeutralGitHub Issue
How to reproduce your results on WMT'14 ENDE datasets of "Attention is All You Need"?
“Hi, I want to reproduce the results on WMT'14 ENDE datasets of "Attention is All You Need" paper. I have read [OpenNMT-FAQ]( and I want to know the exact details about your experiments: 1. Did you do the BPE or word spiece? 2. What's the exact BLEU score of your experiments on…”