runtime error

Exit code: 1. Reason: 🔹 Loading tokenizer... tokenizer_config.json: 0%| | 0.00/178k [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 178k/178k [00:00<00:00, 104MB/s] vocab.json: 0%| | 0.00/2.47M [00:00<?, ?B/s] vocab.json: 100%|██████████| 2.47M/2.47M [00:00<00:00, 25.6MB/s] tokenizer.json: 0%| | 0.00/9.27M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 9.27M/9.27M [00:00<00:00, 114MB/s] added_tokens.json: 0%| | 0.00/53.0 [00:00<?, ?B/s] added_tokens.json: 100%|██████████| 53.0/53.0 [00:00<00:00, 343kB/s] special_tokens_map.json: 0%| | 0.00/558 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 558/558 [00:00<00:00, 3.84MB/s] 🔹 Setting up 4-bit quantization... 🔹 Loading base model... config.json: 0%| | 0.00/684 [00:00<?, ?B/s] config.json: 100%|██████████| 684/684 [00:00<00:00, 3.66MB/s] Traceback (most recent call last): File "/app/app.py", line 35, in <module> base_model_obj = AutoModelForCausalLM.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 564, in from_pretrained return model_class.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3398, in from_pretrained hf_quantizer.validate_environment( File "/usr/local/lib/python3.10/site-packages/transformers/quantizers/quantizer_bnb_4bit.py", line 62, in validate_environment raise RuntimeError("No GPU found. A GPU is needed for quantization.") RuntimeError: No GPU found. A GPU is needed for quantization.

Container logs: