Bruno Pio

> > Maybe the filter have the period of the data plan too. > > Would be nice. > > It does. When you're on a custom plan, you have...

> > I'm in a custom plan but it didn't appear... > > Are you running the latest version of the app? Yes, v2.3.2.

> > Yes, v2.3.2. > > Should work fine then. Could you try switching data plans. So "this month" and others are for data plan? Ok thanks I thought it...

> > So "this month" and others are for data plan? > > My point was, if you have a custom data plan set, you get an additional option "Current...

Sorry... I am only an user of java... not a developer. > You can already translate Dark Exchange buy creating a new Terms_XX.properties file where XX is the language code...

> Just want to share that I've successfully installed Triton on Windows and called `torch.compile`: [jakaline-dev/Triton_win#2](https://github.com/jakaline-dev/Triton_win/issues/2) > > Update: I've published Triton wheels in my fork, and `torchao.quantization.autoquant` just works...

Waiting for this!

Just for curiosity, what miss to merge?

now model.save_pretrained(save_path) give this: ``` Traceback (most recent call last): File "C:\Users\Admin\Desktop\Python\0.LLMs\hqq\hqq1b.py", line 35, in model.save_pretrained(save_path) File "C:\Users\Admin\Desktop\Python\0.LLMs\hqq\venv\Lib\site-packages\transformers\modeling_utils.py", line 2932, in save_pretrained state_dict_split = split_torch_state_dict_into_shards( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Admin\Desktop\Python\0.LLMs\hqq\venv\Lib\site-packages\huggingface_hub\serialization\_torch.py", line 330,...

> @blap is this related to the latest transformer changes? Otherwise, which hqq version causes this? I think so. I didn't had this problem in the release of hqq in...