Andrew Zhu comments

Results 10 comments of


                                            Andrew Zhu

ssh key

the same ask

ValueError: Tokenizer class LLaMATokenizer does not exist or is not currently imported.

> For anybody interested I was able to load an earlier saved model with the same issue using my [fork](https://github.com/mbehm/transformers) with the capitalization restored. That being said for future it's...

ImportError: DLL load failed while importing exllama_ext: 找不到指定的模块。

solved the problem, use nvcc --version to find out your cuda version, if your cuda is 12.1. Then install the 12.1 torch. pip3 install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu121

DLL load failed while importing inplace_abn: 找不到指定的模块。

The same issue, too many errors

请问为什么添加flash加速后，就会出现The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results. Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.

see the same error

SD3 Token Limit?

Working on overcoming all three text model's token limitations with prompt weighting, seems working good, one preview sample: ![image](https://github.com/huggingface/diffusers/assets/7898116/f099fa62-54c5-497e-9e77-3fd012639824)

SD3 Token Limit?

> I think it's ok to close it, I'll probably open a discussion about it at a later time with some insights I found about this. @xhinker are you going...

SD3 Token Limit?

@asomoza @neuron-party Upload the module that supports long prompt weighted prompt for **SD3(unlimited for 2 CLIP, 512 max for T5)**, **SDXL** and **SD15**. https://github.com/xhinker/sd_embed

Integrate Lumina-T2X

This model is SO cool

我的 35 岁

用Issue 做Blog，完美！