when I run command:
optimum-cli export onnx --model meta-llama/Llama-3.2-11B-Vision-Instruct ./
shows error:
KeyError: "Unknown task: image-text-to-text. Possible values are: audio-classification for AutoModelForAudioClassification, audio-frame-classification for AutoModelForAudioFrameClassification, audio-xvector for AutoModelForAudioXVector, automatic-speech-recognition for ('AutoModelForSpeechSeq2Seq', 'AutoModelForCTC'), depth-estimation for AutoModelForDepthEstimation, feature-extraction for AutoModel, fill-mask for AutoModelForMaskedLM, image-classification for AutoModelForImageClassification, image-segmentation for ('AutoModelForImageSegmentation', 'AutoModelForSemanticSegmentation'), image-to-image for AutoModelForImageToImage, image-to-text for AutoModelForVision2Seq, mask-generation for AutoModel, masked-im for AutoModelForMaskedImageModeling, multiple-choice for AutoModelForMultipleChoice, object-detection for AutoModelForObjectDetection, question-answering for AutoModelForQuestionAnswering, semantic-segmentation for AutoModelForSemanticSegmentation, text-to-audio for ('AutoModelForTextToSpectrogram', 'AutoModelForTextToWaveform'), text-generation for AutoModelForCausalLM, text2text-generation for AutoModelForSeq2SeqLM, text-classification for AutoModelForSequenceClassification, token-classification for AutoModelForTokenClassification, zero-shot-image-classification for AutoModelForZeroShotImageClassification, zero-shot-object-detection for AutoModelForZeroShotObjectDetection"
Is this model supported by any plans? Or is there any way I can modify the code to support new tasks?
when I run command:
optimum-cli export onnx --model meta-llama/Llama-3.2-11B-Vision-Instruct ./shows error: KeyError: "Unknown task: image-text-to-text. Possible values are:
audio-classificationfor AutoModelForAudioClassification,audio-frame-classificationfor AutoModelForAudioFrameClassification,audio-xvectorfor AutoModelForAudioXVector,automatic-speech-recognitionfor ('AutoModelForSpeechSeq2Seq', 'AutoModelForCTC'),depth-estimationfor AutoModelForDepthEstimation,feature-extractionfor AutoModel,fill-maskfor AutoModelForMaskedLM,image-classificationfor AutoModelForImageClassification,image-segmentationfor ('AutoModelForImageSegmentation', 'AutoModelForSemanticSegmentation'),image-to-imagefor AutoModelForImageToImage,image-to-textfor AutoModelForVision2Seq,mask-generationfor AutoModel,masked-imfor AutoModelForMaskedImageModeling,multiple-choicefor AutoModelForMultipleChoice,object-detectionfor AutoModelForObjectDetection,question-answeringfor AutoModelForQuestionAnswering,semantic-segmentationfor AutoModelForSemanticSegmentation,text-to-audiofor ('AutoModelForTextToSpectrogram', 'AutoModelForTextToWaveform'),text-generationfor AutoModelForCausalLM,text2text-generationfor AutoModelForSeq2SeqLM,text-classificationfor AutoModelForSequenceClassification,token-classificationfor AutoModelForTokenClassification,zero-shot-image-classificationfor AutoModelForZeroShotImageClassification,zero-shot-object-detectionfor AutoModelForZeroShotObjectDetection"Is this model supported by any plans? Or is there any way I can modify the code to support new tasks?