AI PC: Text2Text Generation
Text2Text Generation LLMs that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU.
Updated • 7.47k • 468Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForSeq2SeqLM library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
facebook/m2m100_418M
Updated • 451k • 350Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForSeq2SeqLM library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
facebook/mbart-large-50-many-to-one-mmt
Updated • 834 • 67Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForSeq2SeqLM library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
google/mt5-base
Updated • 44.1k • 266Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForSeq2SeqLM library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
google/mt5-large
Updated • 131k • 108Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForSeq2SeqLM library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
google/mt5-small
Updated • 211k • 192Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForSeq2SeqLM library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
ku-nlp/bart-base-japanese
Updated • 180 • 10Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForSeq2SeqLM library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
transformersbook/pegasus-samsum
Updated • 69 • 7Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForSeq2SeqLM library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation
zhenchuan/marian-finetuned-kde4-en-to-cn-accelerate
77.5M • Updated • 11 • 1Note This model was tested with OpenVINO version 2024.1.0 using the OVModelForSeq2SeqLM library. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation