Get the latest tech news
Large Concept Models: Language modeling in a sentence representation space
Large Concept Models: Language modeling in a sentence representation space - facebookresearch/large_concept_model
The LCM is a sequence-to-sequence model in the concepts space trained to perform auto-regressive sentence prediction. Note that we only provide requirements for cpu dependencies, if you want to use GPU support, you will have to choose the variants of torch and fairseq2 that work for your system. To register the selected checkpoint, copy the automatically created yaml file to./lcm/cards/mycards.yaml and rename the model to replace the default on_the_fly_lcm../lcm/cards/mycards.yaml will look like:
Or read this on Hacker News