runtime error

| 3.44G/3.44G [01:03<00:00, 54.0MB/s] Fetching 15 files: 87%|████████▋ | 13/15 [01:04<00:08, 4.42s/it] Fetching 15 files: 100%|██████████| 15/15 [01:04<00:00, 4.30s/it] Cannot initialize model with low cpu memory usage because `accelerate` was not found in the environment. Defaulting to `low_cpu_mem_usage=False`. It is strongly recommended to install `accelerate` for faster and less memory-intense model loading. You can do so with: ``` pip install accelerate ``` . Loading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s] Loading pipeline components...: 14%|█▍ | 1/7 [00:05<00:31, 5.26s/it] Loading pipeline components...: 29%|██▊ | 2/7 [00:14<00:36, 7.34s/it] Loading pipeline components...: 43%|████▎ | 3/7 [00:14<00:16, 4.09s/it] Loading pipeline components...: 57%|█████▋ | 4/7 [00:15<00:08, 2.82s/it]`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["id2label"]` will be overriden. `text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["bos_token_id"]` will be overriden. `text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["eos_token_id"]` will be overriden. Loading pipeline components...: 71%|███████▏ | 5/7 [00:21<00:08, 4.00s/it] Loading pipeline components...: 100%|██████████| 7/7 [00:21<00:00, 3.04s/it] Traceback (most recent call last): File "/home/user/app/main.py", line 17, in <module> gr.Interface.from_pipeline(pipeline) File "/home/user/.local/lib/python3.10/site-packages/gradio/interface.py", line 120, in from_pipeline interface_info = load_from_pipeline(pipeline) File "/home/user/.local/lib/python3.10/site-packages/gradio/pipelines.py", line 29, in load_from_pipeline raise ValueError("pipeline must be a transformers.Pipeline") ValueError: pipeline must be a transformers.Pipeline

Container logs: