2024-07-10 04:41:59 | INFO | model_worker | args: Namespace(host='0.0.0.0', port=40001, worker_address='http://10.140.60.25:40001', controller_address='http://10.140.60.209:10075', model_path='share_internvl/InternVL2-1B/', model_name=None, device='cuda', limit_model_concurrency=5, stream_interval=1, load_8bit=False) 2024-07-10 04:41:59 | INFO | model_worker | Loading the model InternVL2-1B on worker 19edde ... 2024-07-10 04:41:59 | WARNING | transformers.tokenization_utils_base | Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 2024-07-10 04:41:59 | WARNING | transformers.tokenization_utils_base | Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 2024-07-10 04:42:01 | INFO | model_worker | Register to controller 2024-07-10 04:42:01 | ERROR | stderr | INFO: Started server process [99741] 2024-07-10 04:42:01 | ERROR | stderr | INFO: Waiting for application startup. 2024-07-10 04:42:01 | ERROR | stderr | INFO: Application startup complete. 2024-07-10 04:42:01 | ERROR | stderr | INFO: Uvicorn running on http://0.0.0.0:40001 (Press CTRL+C to quit) 2024-07-10 04:42:16 | INFO | model_worker | Send heart beat. Models: ['InternVL2-1B']. Semaphore: None. global_counter: 0 2024-07-10 04:42:31 | INFO | model_worker | Send heart beat. Models: ['InternVL2-1B']. Semaphore: None. global_counter: 0 2024-07-10 04:42:46 | INFO | model_worker | Send heart beat. Models: ['InternVL2-1B']. Semaphore: None. global_counter: 0 2024-07-10 04:43:00 | INFO | stdout | INFO: 10.140.60.209:55826 - "POST /worker_get_status HTTP/1.1" 200 OK 2024-07-10 04:43:01 | INFO | model_worker | Send heart beat. Models: ['InternVL2-1B']. Semaphore: None. global_counter: 0 2024-07-10 04:43:15 | INFO | stdout | INFO: 10.140.60.209:55900 - "POST /worker_get_status HTTP/1.1" 200 OK 2024-07-10 04:43:16 | INFO | stdout | INFO: 10.140.60.209:55938 - "POST /worker_get_status HTTP/1.1" 200 OK 2024-07-10 04:43:17 | INFO | model_worker | Send heart beat. Models: ['InternVL2-1B']. Semaphore: None. global_counter: 0 2024-07-10 04:43:17 | INFO | model_worker | Send heart beat. Models: ['InternVL2-1B']. Semaphore: Semaphore(value=4, locked=False). global_counter: 1 2024-07-10 04:43:17 | INFO | stdout | INFO: 10.140.60.209:55960 - "POST /worker_generate_stream HTTP/1.1" 200 OK 2024-07-10 04:43:17 | INFO | stdout | history: [] 2024-07-10 04:43:17 | INFO | stdout | question: Image-1: 2024-07-10 04:43:17 | INFO | stdout | Describe this image in detail. 2024-07-10 04:43:17 | INFO | stdout | pil_images: [] 2024-07-10 04:43:17 | INFO | model_worker | dynamic_image_size: True 2024-07-10 04:43:17 | INFO | model_worker | use_thumbnail: True 2024-07-10 04:43:17 | INFO | model_worker | Resize images to 448x448 2024-07-10 04:43:17 | INFO | model_worker | Split images to torch.Size([10, 3, 448, 448]) 2024-07-10 04:43:17 | ERROR | stderr | Exception in thread Thread-2 (chat): 2024-07-10 04:43:17 | ERROR | stderr | Traceback (most recent call last): 2024-07-10 04:43:17 | ERROR | stderr | File "/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl-apex/lib/python3.10/threading.py", line 1009, in _bootstrap_inner 2024-07-10 04:43:18 | ERROR | stderr | self.run() 2024-07-10 04:43:18 | ERROR | stderr | File "/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl-apex/lib/python3.10/threading.py", line 946, in run 2024-07-10 04:43:18 | ERROR | stderr | self._target(*self._args, **self._kwargs) 2024-07-10 04:43:18 | ERROR | stderr | File "/mnt/petrelfs/wangweiyun/.cache/huggingface/modules/transformers_modules/InternVL2-1B/modeling_internvl_chat.py", line 280, in chat 2024-07-10 04:43:18 | ERROR | stderr | generation_output = self.generate( 2024-07-10 04:43:18 | ERROR | stderr | File "/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl-apex/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context 2024-07-10 04:43:18 | ERROR | stderr | return func(*args, **kwargs) 2024-07-10 04:43:18 | ERROR | stderr | File "/mnt/petrelfs/wangweiyun/.cache/huggingface/modules/transformers_modules/InternVL2-1B/modeling_internvl_chat.py", line 330, in generate 2024-07-10 04:43:18 | ERROR | stderr | outputs = self.language_model.generate( 2024-07-10 04:43:18 | ERROR | stderr | TypeError: transformers.generation.utils.GenerationMixin.generate() got multiple values for keyword argument 'use_cache' 2024-07-10 04:43:27 | INFO | stdout | Caught Unknown Error 2024-07-10 04:43:27 | INFO | model_worker | Send heart beat. Models: ['InternVL2-1B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1 2024-07-10 04:43:32 | INFO | model_worker | Send heart beat. Models: ['InternVL2-1B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1