Edd
Edd
Hello, I just learn about SetFit and now I want to use it for my ABSA usecase. I have 50.000 row of datasets which the maximum token per row is...
`_prepare_4d_causal_attention_mask_for_sdpa` only accept float mask and bool mask After thinking about it, it makes sense to do it that way since we want `softmax` on attention to be zero on...
People complaining that they can't use the LoRA with VLLM because `load_lora` method is not available. This is because when loading a LoRA model, `get_peft_model` goes into the `Unsloth: Already...