-
@versae Hey there, I am too pretraining T5_1_1 base using a custom generated datasets that's in huggingface. your repo has been a huge help in making HF dataset compatible.
upon making a task.py …
-
**Describe the bug**
I have mt5 model, which is converted from pytorch to onnx and now i am trying to load a model into onnxruntime, i found out following error. Maybe due to limit specified in code …
-
### System Info
win10
python 3.8.4
pytorch 12.1 cpu
transformers4.22.2
optimum 1.4.0
onnxruntime 1.12.1
### Who can help?
@Narsil
@patil-suraj
### Information
- [X] The official example scr…
-
It seems like real world use of TLS certificate compression will likely use Brotli.
https://github.com/google/brotli
https://www.chromestatus.com/feature/5696925844111360
https://bugzilla.mozilla…
-
Processing JENDL5 U235 fails on ACER in the standard processing path for continuous energy ACE files using NJOY2016.66.
An example input file: [U235.inp.txt](https://github.com/njoy/NJOY2016/files/…
-
How to draw the mplfinance cnadlesticks drawing to the canvas instead of generating the blank canvas k-line drawing as shown in the figure, but drawing it in the plot output bar of python,how to corre…
-
### System Info
```shell
Optimum: 1.4.1.dev0
torch: 1.12.1+cu116
onnx: 1.12.0
onnxruntime-gpu: 1.12.1
python: 3.8.13
CUDA: 11.6
cudnn: 8.4.1
RTX 3090
```
### Who can help?
@JingyaH…
-
Hi,
I can reproduce mt5-base-enc, mt5-base-t2t models, including training on full datasets and zero-shot training. As for the xlmr-base model. I can reproduce the results training on the full datas…
-
# User Agents
A User-Agent string is useful to let server mods to easily handle different type of Minetest clients, just like what websites do. Minetest servers can then give the best playing exper…
-
Hi!
I'm trying to use you library to trim MBART but it produces the following error:
```python
# trim model
mt = MBartTrimmer(model, config, tt.trimmed_tokenizer)
mt.make_weights(tt.trimmed_v…