runtime error

97%|███████████████▌| 3.97G/4.08G [01:40<00:02, 41.5MB/s] ggml-model-q4_k.gguf: 97%|███████████████▌| 3.97G/4.08G [01:40<00:03, 28.3MB/s] ggml-model-q4_k.gguf: 98%|███████████████▌| 3.98G/4.08G [01:40<00:02, 39.5MB/s] ggml-model-q4_k.gguf: 98%|███████████████▋| 3.99G/4.08G [01:40<00:01, 49.5MB/s] ggml-model-q4_k.gguf: 98%|███████████████▋| 4.00G/4.08G [01:41<00:01, 48.5MB/s] ggml-model-q4_k.gguf: 98%|███████████████▋| 4.01G/4.08G [01:41<00:02, 36.1MB/s] ggml-model-q4_k.gguf: 98%|███████████████▋| 4.01G/4.08G [01:41<00:01, 43.4MB/s] ggml-model-q4_k.gguf: 99%|███████████████▊| 4.02G/4.08G [01:41<00:01, 30.6MB/s] ggml-model-q4_k.gguf: 99%|███████████████▊| 4.03G/4.08G [01:42<00:01, 42.1MB/s] ggml-model-q4_k.gguf: 99%|███████████████▊| 4.04G/4.08G [01:42<00:01, 39.5MB/s] ggml-model-q4_k.gguf: 99%|███████████████▊| 4.05G/4.08G [01:42<00:00, 42.6MB/s] ggml-model-q4_k.gguf: 100%|███████████████▉| 4.06G/4.08G [01:42<00:00, 57.4MB/s] ggml-model-q4_k.gguf: 100%|███████████████▉| 4.07G/4.08G [01:42<00:00, 42.0MB/s] ggml-model-q4_k.gguf: 100%|███████████████▉| 4.08G/4.08G [01:43<00:00, 43.6MB/s] ggml-model-q4_k.gguf: 100%|████████████████| 4.08G/4.08G [01:43<00:00, 39.5MB/s] Download Completed. Traceback (most recent call last): File "/home/user/app/app.py", line 22, in <module> from llama_cpp import Llama, clip_model_load, llava_image_embed_make_with_filename, llava_image_embed_make_with_bytes, llava_image_embed_p, llava_image_embed_free, llava_validate_embed_size, llava_eval_image_embed ModuleNotFoundError: No module named 'llama_cpp'

Container logs: