-
### Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
### What happened?
loading stable diffusion model: RuntimeError
Traceback (…
-
### System Info
When I'm inspecting the cross-attention layers from the pretrained transformer translation model (MarianMT model), It is very strange that the cross attention from layer 0 and 1 provi…
-
Hello,
I have a question on the seq-to-seq model tracing in this [tutorial](https://awsdocs-neuron.readthedocs-hosted.com/en/latest/src/examples/pytorch/transformers-marianmt.html). The example sh…
-
I have used the CTranslate2 inference within bentoML (https://github.com/OpenNMT/CTranslate2) with custom runner.
But, when trying to save the model with cloudpickle, it results in the following er…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
### What happened?
Nor the Localization Extension for Italian Language (but …
-
```
Error loading script: sonar.py
Traceback (most recent call last):
File "/content/drive/My Drive/ai/stable-diffusion-webui/modules/scripts.py", line 229, in load_scripts
script_module = s…
-
Hi team,
We are trying to compile a sequence-to-sequence model using torch_neuronx. The code works fine with 'torch_neuron' and we can get the neuron traced model successfully. But when using torc…
-
Hi team,
I am trying to neuron trace an NLP model called DeltaLM, which is a transformers encoder&decoder model for text summarization tasks. This model can be imported from this [huggingface model…
-
Hi, I have tried training a MarianMT model by maximizing bert_score, and everything worked fine until I was trying to load these weights from transformers, when I encountered an issue.
I have creat…
-
tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-swc")
def translate(text):
translated = model22.generate(**tokenizer(text, return_tensors="pt", padding=True).to("cpu"))
r…