runtime error

Downloading shards: 14%|█▍ | 1/7 [00:13<01:18, 13.05s/it] Downloading shards: 29%|██▊ | 2/7 [00:52<02:21, 28.36s/it] Downloading shards: 43%|████▎ | 3/7 [01:37<02:25, 36.27s/it] Downloading shards: 57%|█████▋ | 4/7 [02:12<01:46, 35.48s/it] Downloading shards: 71%|███████▏ | 5/7 [02:51<01:13, 36.88s/it] Downloading shards: 86%|████████▌ | 6/7 [03:29<00:37, 37.41s/it] Downloading shards: 100%|██████████| 7/7 [03:59<00:00, 34.98s/it] Downloading shards: 100%|██████████| 7/7 [03:59<00:00, 34.27s/it] Traceback (most recent call last): File "/home/user/app/app.py", line 4, in <module> from bot import chatbot, model_inference, BOT_AVATAR, EXAMPLES, model_selector, decoding_strategy, temperature, max_new_tokens, repetition_penalty, top_p File "/home/user/app/bot.py", line 31, in <module> "idefics2-8b-chatty": Idefics2ForConditionalGeneration.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3620, in from_pretrained config = cls._autoset_attn_implementation( File "/usr/local/lib/python3.10/site-packages/transformers/models/idefics2/modeling_idefics2.py", line 1381, in _autoset_attn_implementation config = super()._autoset_attn_implementation( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1469, in _autoset_attn_implementation cls._check_and_enable_flash_attn_2( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1580, in _check_and_enable_flash_attn_2 raise ImportError(f"{preface} Flash Attention 2 is not available. {install_message}") ImportError: FlashAttention2 has been toggled on, but it cannot be used due to the following error: Flash Attention 2 is not available. Please refer to the documentation of https://huggingface.co/docs/transformers/perf_infer_gpu_one#flashattention-2 to install Flash Attention 2.

Container logs: