fxmarty
fxmarty
cc @giuseppe5 @nickfraser we hit the same issue.
@gramalingam In our case, `convert_attribute=True` fixed the issue. It could be helpful to update the error message.
Hi, thank you for the suggestion, SDPA support for mistral was added by @ArthurZucker in https://github.com/huggingface/transformers/pull/28133, maybe he has more insight.
Fixed in https://github.com/huggingface/transformers/pull/30127
Thank you, would you like to try and work on it? I will add it to my todo otherwise.
Hi @sanjeevk-os, for sure, feel free to ping me when you submit a PR!
Hi @ingo-m, thank you for the report. Locally, how did you install `onnxruntime-gpu`? The wheel hosted on PyPI index is for CUDA 11.8. https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html gives instructions on how to install...
@ingo-m I can not reproduce the issue with: ```python import torch from optimum.onnxruntime import ORTModelForCausalLM from transformers import AutoModelForCausalLM, AutoTokenizer base_model_name = "bigscience/bloomz-560m" device_name = "cuda" tokenizer = AutoTokenizer.from_pretrained(base_model_name) ort_model...
@antoniovazquezblanco I believe the correct syntax should be: ``` - name: Checkout uses: actions/checkout@v3 with: ref: "refs/pull/${{ github.event.number }}/merge" fetch-depth: 2 # Important security check: https://github.com/actions/checkout/issues/518 - name: Sanity check...