runtime error

Exit code: 1. Reason: | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:02<00:02, 2.28s/it] Loading checkpoint shards: 100%|██████████| 2/2 [00:03<00:00, 1.78s/it] Loading checkpoint shards: 100%|██████████| 2/2 [00:03<00:00, 1.86s/it] generation_config.json: 0%| | 0.00/249 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 249/249 [00:00<00:00, 2.11MB/s] Base model loaded. Loading LoRA adapter: jinv2/qwen-1_8b-hemiplegia-lora... adapter_config.json: 0%| | 0.00/794 [00:00<?, ?B/s] adapter_config.json: 100%|██████████| 794/794 [00:00<00:00, 5.63MB/s] The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable. adapter_model.safetensors: 0%| | 0.00/26.9M [00:00<?, ?B/s] adapter_model.safetensors: 100%|██████████| 26.9M/26.9M [00:00<00:00, 128MB/s] Error loading LoRA adapter: We need an `offload_dir` to dispatch this model according to this `device_map`, the following submodules need to be offloaded: base_model.model.transformer.ln_f, base_model.model.lm_head, base_model.model.transformer.h. Traceback (most recent call last): File "/home/user/app/app.py", line 64, in <module> model = PeftModel.from_pretrained(base_model, lora_adapter_id) File "/usr/local/lib/python3.10/site-packages/peft/peft_model.py", line 541, in from_pretrained load_result = model.load_adapter( File "/usr/local/lib/python3.10/site-packages/peft/peft_model.py", line 1330, in load_adapter dispatch_model( File "/usr/local/lib/python3.10/site-packages/accelerate/big_modeling.py", line 380, in dispatch_model raise ValueError( ValueError: We need an `offload_dir` to dispatch this model according to this `device_map`, the following submodules need to be offloaded: base_model.model.transformer.ln_f, base_model.model.lm_head, base_model.model.transformer.h.

Container logs: