Loading doesn't seem right.

[Phrixus2023]

D:\BaiduNetdiskDownload\Omost20240604\venv\lib\site-packages\transformers\utils\hub.py:124: FutureWarning: Using TRANSFORMERS_CACHE is deprecated and will be removed in v5 of Transformers. Use HF_HOME instead. warnings.warn( D:\BaiduNetdiskDownload\Omost20240604\lib_omost\pipeline.py:64: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requiresgrad(True), rather than torch.tensor(sourceTensor). alphas_cumprod = torch.tensor(np.cumprod(alphas, axis=0), dtype=torch.float32) Unload to CPU: AutoencoderKL Unload to CPU: CLIPTextModel Unload to CPU: UNet2DConditionModel Unload to CPU: CLIPTextModel Unused kwargs: ['_load_in_4bit', '_load_in_8bit', 'quant_method']. These kwargs are not used in <class 'transformers.utils.quantization_config.BitsAndBytesConfig'>. Downloading shards: 100%|██████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 1830.37it/s] Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 2/2 [00:08<00:00, 4.16s/it] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. You shouldn't move a model that is dispatched using accelerate hooks. Unload to CPU: LlamaForCausalLM Running on local URL: http://0.0.0.0:7860

To create a public link, set share=True in launch().

[Phrixus2023]

And in the case of multiple graphics cards it causes confusion as to which graphics card to load to.

[departurechen]

same issue here, anybody can solve this?

[Phrixus2023]

same issue here, anybody can solve this?

I probably solved it because there were multiple graphics cards running, and I needed to disable the extra cards to keep just one and then re-run the programme.