Bug Report hello i am using https://huggingface.co/Ahmad/parsT5-base model i want toe xport it to onnx using "python -m transformers.onnx --model="Ahmad/parsT5-base" onnx/" but i get this error: /usr/local/lib/python3.10/dist-packages/to...
Hello, I am new and want to try converting models to Onnx format and I have the following issue. I have a model that has been quantized to 4-bit, and then I converted this model to Onnx. My quantized model has a weight size of 7GB, but when I run the conversion to Onnx, my ...
model = onnx.load(src_model_path+'/gpt2-xl-huggingface-op13-padding-step1.onnx') onnx.save(model, dst_model_path+'/gpt2-xl-huggingface-op13-padding-step1.onnx', save_as_external_data=True, all_tensors_to_one_file=True, location='gpt2-xl-huggingface-op13-padding-step1.weights')...
Describe the bug Trying to export the unet model to onnx. Used this script .onnx file created successfully but export wasn't successful: import onnx onnx_model = onnx.load("model.onnx") onnx.checker.check_model(onnx_model) Error: protobu...
model.clip import BICUBIC, _convert_image_to_rgb from clip_server.model.clip_onnx import _MODELS, _S3_BUCKET_V2, CLIPOnnxModel, download_model from clip_server.model.pretrained_models import _VISUAL_MODEL_IMAGE_SIZE from clip_server.model.tokenization import Tokenizer from huggingface_hub import...
huggingface/optimumPublic NotificationsYou must be signed in to change notification settings Fork487 Star2.7k New issue Merged fxmartymerged 2 commits intohuggingface:mainfromfxmarty:support-clip-vision-model Jul 11, 2024 +21−0 Conversation3Commits2Checks122Files changed3 ...
Adds ONNX export support for https://huggingface.co/alibaba-damo/mgp-str-base Fixes # (issue) Before submitting This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). Did you make sure to update the documentation with your changes? Did you wr...
Feature request Currently optimum provides for exporting CLIP models from transformers to onnx however there is no feature to do this for CLIPVisionModel. I believe the code for exporting this class would already be present in the librar...
🚀 The feature, motivation and pitch We are attempting to export a quantized llama model (from HuggingFace) to ONNX but are running into an unsupported op error for bitwise_right_shift: torch.onnx.errors.UnsupportedOperatorError: Exportin...
Imagine trying to export someone else's model from GitHub or HuggingFace or elsewhere and running into this error! Collaborator thiagocrepaldi commented Mar 23, 2023 We are still looking into it, just provided a naive workaround in case you were blocked. 👍 1 thiagocrepaldi assigned shubham...