Difference between revisions of "NLP"

From UFRC
Jump to navigation Jump to search
m (Maxprok moved page NLP to Nlp)
Line 18: Line 18:
 
{{App_Description|app={{#var:app}}|url={{#var:url}}|name={{#var:app}}}}|}}
 
{{App_Description|app={{#var:app}}|url={{#var:url}}|name={{#var:app}}}}|}}
  
A collection of natural language processing libraries. This includes but not limited to:
+
This page describes the collection of natural language processing software on HiPerGator.  
* pytorch
 
* torchtext
 
* rapidsai
 
* bertopic
 
* nltk
 
* gensim
 
* spacy
 
* scikit-learn
 
  
  
 
<!--Modules-->
 
<!--Modules-->
==Environment Modules==
+
==Environment Modules for NLP==
Run <code>module spider {{#var:app}}</code> to find out what environment modules are available for this application.
+
*'''nlp:''' module load nlp will provide a Python environment with spacy, pytorch, torchtext, nltk, sentencepiece, transformers, sentence-transformers, bertopic, RAPIDSai, gensim, scikit-learn, and more.
==System Variables==
+
*'''nemo:''' module load nemo will provide a singularity container environment with Python and Nvidia NeMo. NeMo has NLP task training, plus speech-to-text and text-to-speech models.
* HPC_{{uc:{{#var:app}}}}_DIR - installation directory
+
*'''pytorch:''' Note, use module spider pytorch to list the version we have available. Beyond stock pytorch versions, we have the Nvidia pytorch singularity container with the Apex optimizers required for Megatron-LM. Use module load ngc-pytorch to access this container, and you can run Megatron from source code. 
* HPC_{{uc:{{#var:app}}}}_BIN - executable directory
 
  
 
<!--Configuration-->
 
<!--Configuration-->

Revision as of 17:25, 26 July 2021


This page describes the collection of natural language processing software on HiPerGator.


Environment Modules for NLP

  • nlp: module load nlp will provide a Python environment with spacy, pytorch, torchtext, nltk, sentencepiece, transformers, sentence-transformers, bertopic, RAPIDSai, gensim, scikit-learn, and more.
  • nemo: module load nemo will provide a singularity container environment with Python and Nvidia NeMo. NeMo has NLP task training, plus speech-to-text and text-to-speech models.
  • pytorch: Note, use module spider pytorch to list the version we have available. Beyond stock pytorch versions, we have the Nvidia pytorch singularity container with the Apex optimizers required for Megatron-LM. Use module load ngc-pytorch to access this container, and you can run Megatron from source code.