-
I appreciate your help suddenly i am getting this error when do training.
OSError Traceback (most recent call last)
in ()
58 BertEmbeddings(bert_mode…
-
I am trying to understand the method in which GCN output is passed into the BERT model
The section of code this happens is in [model_vgcn_bert.py](https://github.com/Louis-udm/VGCN-BERT/blob/master…
-
### What happened?
For the give IR ( IREE compiler version 20241024.1057 @ 9c5b57a8b9e6981e300df02c41a296bd49e07c99 )
```mlir
module {
func.func @main_graph(%arg0: !torch.vtensor, %arg1: !torch.v…
-
We need to create some text classification techniques.
-
I fine-tuning a classification model using bert, however the inference time on CPU is so long,
I run the inference process is so long. It takes nearly 15 seconds for one call (15s is only for predict…
-
we need model evaluation method.
-
### Describe the issue
cuda 10.2
onnx=1.8
onnxruntime-gpu=1.6
For sequnce labeling task (input the token ids, output the start_pos, end_pos), the pytorch use 1.8G, but onnx use 1.9G (although …
-
### Feature request
We should add scan and remat (gradient checkpointing) to the most important Flax/JAX models (BERT, GPT2, OPT, T5, BART, Wav2Vec2).
### Motivation
Scan allows for much faster com…
-
Hi Louis:
Thanks for your contribution and your paper is outstanding! I have some little questions.
May I ask what "gcn_swop_eye" means in the code? And where are they come from (What is the proced…
-
https://github.com/huggingface/tokenizers
```python3
# Tokenizers provides ultra-fast implementations of most current tokenizers:
>>> from tokenizers import (ByteLevelBPETokenizer,
…