Mr.Yu

I meet on this problem: from .modeling_tf_utils import TFPreTrainedModel, get_initializer, keras_serializable, shape_list ImportError: cannot import name 'keras_serializable' The version of huggingface/transformers in my env is 2.10.0.

The Tokenizer takes the token ‘pricerange’ as ‘[UNK]’?

1

For example: tokens: ['i', 'am', 'looking', 'for', 'a', 'restaurant', 'in', 'the', '[restaurant_area]', '.', 'postcode', 'type', 'phone', 'food', 'pricerange', 'address', 'area', 'name', 'id', 'reference'] input_ids: [8, 35, 51, 15, 12, 45,...

RuntimeError: r.nvmlDeviceGetNvLinkRemoteDeviceType_ INTERNAL ASSERT FAILED at "../c10/cuda/driver_api.cpp":27, please report a bug to PyTorch. Can't find nvmlDeviceGetNvLinkRemoteDeviceType: /lib64/libnvidia-ml.so.1: undefined symbol: nvmlDeviceGetNvLinkRemoteDeviceType

1

When I want to use a for loop like this to run multiple results: ```python pipe = CogVideoXPipeline.from_pretrained(...) for prompt in prompts: pipe.enable_sequential_cpu_offload() prompt_embeds, _ = pipe.encode_prompt(prompt=prompt,...) video = pipe(...).frames[0]...