diff --git "a/gradio_web_server.log" "b/gradio_web_server.log" --- "a/gradio_web_server.log" +++ "b/gradio_web_server.log" @@ -4538,3 +4538,2719 @@ 2024-10-20 05:19:40 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 354, in gradio_handler 2024-10-20 05:19:40 | ERROR | stderr | raise gr.Error("GPU task aborted") 2024-10-20 05:19:40 | ERROR | stderr | gradio.exceptions.Error: 'GPU task aborted' +2024-10-20 05:21:23 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=140613572986048&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6ImphZGVjaG9naGFyaVtwcm9dIiwidXVpZCI6bnVsbCwiZXhwIjoxNzI5Mzk0NTQzfQ.GUsmgrRDZzgh_X59qnJ1uLM9qwL2SMAIoVss9lZGkeY "HTTP/1.1 200 OK" +2024-10-20 05:21:23 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=18 +2024-10-20 05:21:23 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=23 +2024-10-20 05:21:23 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[14, 16, 10, 13] +2024-10-20 05:21:23 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=7820d07ad45c827fd58dad5be3f79c3d5b21f66198d45f74628d46721a4f174d&pid=17406 "HTTP/1.1 200 OK" +2024-10-20 05:21:24 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-20 05:21:24 | INFO | stdout | conv mode to gemma +2024-10-20 05:21:24 | INFO | stdout | Input Image Size:(400, 433) +2024-10-20 05:21:24 | INFO | stdout | Input Image Size:(400, 433) +2024-10-20 05:21:24 | INFO | gradio_web_server | ==== request ==== +{'model': 'jadechoghari/Ferret-UI-Gemma2b', 'prompt': 'A chat between a human and an AI that understands visuals. In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. Increasing x moves right; y moves down. Bounding box: [x1, y1, x2, y2]. Image size: 1000x1000. Follow instructions.user\n\ndescribe shortly what do you see\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['8b23f327b90b6211049acd36e3f99975']"} +2024-10-20 05:21:24 | INFO | stdout | Input Image Size:(400, 433) +2024-10-20 05:21:24 | INFO | stdout | eval.json file created successfully. +2024-10-20 05:21:47 | INFO | stdout | Subprocess output: +2024-10-20 05:21:47 | INFO | stdout | +2024-10-20 05:21:47 | INFO | stdout | Subprocess error (if any): +2024-10-20 05:21:47 | INFO | stdout | +2024-10-20 05:21:47 | INFO | stdout | +2024-10-20 05:21:47 | INFO | stdout | Loading checkpoint shards: 0%| | 0/2 [00:00user\n\nexplain what you see in details\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['8b23f327b90b6211049acd36e3f99975']"} +2024-10-20 17:05:08 | INFO | stdout | Input Image Size:(400, 433) +2024-10-20 17:05:08 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=140555119614928&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NDM2NzY4fQ.EuAW-hG-wXH2Sk2bugvTjvC4pQyyUeJIvn9L7o4vUdI "HTTP/1.1 200 OK" +2024-10-20 17:05:09 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=19 +2024-10-20 17:05:09 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=21 +2024-10-20 17:05:09 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[13, 16, 15, 10, 17, 14] +2024-10-20 17:05:10 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=b99df8a4dc1b6f58dc9e8005a8a2f06e49bf245c40bcb89919e310f4b5346361&pid=124923 "HTTP/1.1 200 OK" +2024-10-20 17:05:11 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-20 17:05:11 | ERROR | stderr | Traceback (most recent call last): +2024-10-20 17:05:11 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 256, in thread_wrapper +2024-10-20 17:05:11 | ERROR | stderr | res = future.result() +2024-10-20 17:05:11 | ERROR | stderr | File "/usr/local/lib/python3.10/concurrent/futures/_base.py", line 451, in result +2024-10-20 17:05:11 | ERROR | stderr | return self.__get_result() +2024-10-20 17:05:11 | ERROR | stderr | File "/usr/local/lib/python3.10/concurrent/futures/_base.py", line 403, in __get_result +2024-10-20 17:05:11 | ERROR | stderr | raise self._exception +2024-10-20 17:05:11 | ERROR | stderr | File "/usr/local/lib/python3.10/concurrent/futures/thread.py", line 58, in run +2024-10-20 17:05:11 | ERROR | stderr | result = self.fn(*self.args, **self.kwargs) +2024-10-20 17:05:11 | ERROR | stderr | File "/home/user/app/cli.py", line 40, in run_inference +2024-10-20 17:05:11 | ERROR | stderr | tokenizer, model, image_processor, context_len = load_pretrained_model( +2024-10-20 17:05:11 | ERROR | stderr | TypeError: load_pretrained_model() got an unexpected keyword argument 'device' +2024-10-20 17:05:11 | INFO | httpx | HTTP Request: POST http://device-api.zero/release?allowToken=b99df8a4dc1b6f58dc9e8005a8a2f06e49bf245c40bcb89919e310f4b5346361&fail=true "HTTP/1.1 200 OK" +2024-10-20 17:05:11 | ERROR | stderr | Traceback (most recent call last): +2024-10-20 17:05:11 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 703, in process_events +2024-10-20 17:05:11 | ERROR | stderr | response = await route_utils.call_process_api( +2024-10-20 17:05:11 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 323, in call_process_api +2024-10-20 17:05:11 | ERROR | stderr | output = await app.get_blocks().process_api( +2024-10-20 17:05:11 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2014, in process_api +2024-10-20 17:05:11 | ERROR | stderr | result = await self.call_function( +2024-10-20 17:05:11 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1579, in call_function +2024-10-20 17:05:11 | ERROR | stderr | prediction = await utils.async_iteration(iterator) +2024-10-20 17:05:11 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 691, in async_iteration +2024-10-20 17:05:11 | ERROR | stderr | return await anext(iterator) +2024-10-20 17:05:11 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 685, in __anext__ +2024-10-20 17:05:11 | ERROR | stderr | return await anyio.to_thread.run_sync( +2024-10-20 17:05:11 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync +2024-10-20 17:05:11 | ERROR | stderr | return await get_async_backend().run_sync_in_worker_thread( +2024-10-20 17:05:11 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2441, in run_sync_in_worker_thread +2024-10-20 17:05:11 | ERROR | stderr | return await future +2024-10-20 17:05:11 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 943, in run +2024-10-20 17:05:11 | ERROR | stderr | result = context.run(func, *args) +2024-10-20 17:05:11 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 668, in run_sync_iterator_async +2024-10-20 17:05:11 | ERROR | stderr | return next(iterator) +2024-10-20 17:05:11 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 829, in gen_wrapper +2024-10-20 17:05:11 | ERROR | stderr | response = next(iterator) +2024-10-20 17:05:11 | ERROR | stderr | File "/home/user/app/app.py", line 267, in http_bot +2024-10-20 17:05:11 | ERROR | stderr | extracted_texts = run_inference( +2024-10-20 17:05:11 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 214, in gradio_handler +2024-10-20 17:05:11 | ERROR | stderr | raise res.value +2024-10-20 17:05:11 | ERROR | stderr | TypeError: load_pretrained_model() got an unexpected keyword argument 'device' +2024-10-20 17:06:18 | INFO | gradio_web_server | args: Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-20 17:06:18 | INFO | gradio_web_server | Models: ['jadechoghari/Ferret-UI-Gemma2b'] +2024-10-20 17:06:18 | INFO | gradio_web_server | Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-20 17:06:18 | ERROR | stderr | /usr/local/lib/python3.10/site-packages/gradio/components/chatbot.py:222: UserWarning: You have not specified a value for the `type` parameter. Defaulting to the 'tuples' format for chatbot messages, but this is deprecated and will be removed in a future version of Gradio. Please set type='messages' instead, which uses openai-style 'role' and 'content' keys. +2024-10-20 17:06:18 | ERROR | stderr | warnings.warn( +2024-10-20 17:06:18 | INFO | httpx | HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK" +2024-10-20 17:06:18 | ERROR | stderr | +2024-10-20 17:06:18 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-20 17:06:18 | ERROR | stderr |  +2024-10-20 17:06:18 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-20 17:06:18 | ERROR | stderr | +2024-10-20 17:06:18 | INFO | stdout | Cannot start Node server on any port in the range 7861-7861. +2024-10-20 17:06:18 | INFO | stdout | Please install Node 20 or higher and set the environment variable GRADIO_NODE_PATH to the path of your Node executable. +2024-10-20 17:06:18 | INFO | stdout | You can explicitly specify a port by setting the environment variable GRADIO_NODE_PORT. +2024-10-20 17:06:18 | INFO | stdout | * Running on local URL: http://0.0.0.0:7860, with SSR ⚡ +2024-10-20 17:06:18 | INFO | httpx | HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK" +2024-10-20 17:06:18 | INFO | httpx | HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK" +2024-10-20 17:06:18 | ERROR | stderr | /usr/local/lib/python3.10/site-packages/gradio/blocks.py:2595: UserWarning: Setting share=True is not supported on Hugging Face Spaces +2024-10-20 17:06:18 | ERROR | stderr | warnings.warn( +2024-10-20 17:06:18 | INFO | stdout | +2024-10-20 17:06:18 | INFO | stdout | To create a public link, set `share=True` in `launch()`. +2024-10-20 17:06:28 | INFO | stdout | conv mode to gemma +2024-10-20 17:06:28 | INFO | stdout | Input Image Size:(400, 433) +2024-10-20 17:06:28 | INFO | stdout | Input Image Size:(400, 433) +2024-10-20 17:06:28 | INFO | gradio_web_server | ==== request ==== +{'model': 'jadechoghari/Ferret-UI-Gemma2b', 'prompt': 'A chat between a human and an AI that understands visuals. In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. Increasing x moves right; y moves down. Bounding box: [x1, y1, x2, y2]. Image size: 1000x1000. Follow instructions.user\n\ndescribe the image in details\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['8b23f327b90b6211049acd36e3f99975']"} +2024-10-20 17:06:28 | INFO | stdout | Input Image Size:(400, 433) +2024-10-20 17:06:28 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=139933519567824&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NDM2ODQ4fQ.lOIguOxq-qAkWuUmWFXEQ5uRobpRk8ITz6YfsKg1Jz8 "HTTP/1.1 200 OK" +2024-10-20 17:06:39 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=14 +2024-10-20 17:06:39 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=18 +2024-10-20 17:06:39 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[15, 17, 10] +2024-10-20 17:06:41 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=eebcff088cba1bb812d21b25bf8992a7ba76ffa043e56e0dacd24db4b6b0b4b2&pid=125383 "HTTP/1.1 200 OK" +2024-10-20 17:06:42 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-20 17:06:44 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-20 17:06:44 | ERROR | stderr | +2024-10-20 17:06:44 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00 +2024-10-20 17:06:50 | ERROR | stderr | image_patches = [processor.preprocess(image_patch, return_tensors='pt')['pixel_values'][0] +2024-10-20 17:06:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/transformers/models/clip/image_processing_clip.py", line 325, in preprocess +2024-10-20 17:06:50 | ERROR | stderr | image = self.resize(image=image, size=size, resample=resample, input_data_format=input_data_format) +2024-10-20 17:06:50 | ERROR | stderr | File "/home/user/.cache/huggingface/modules/transformers_modules/jadechoghari/Ferret-UI-Gemma2b/28bcebb3965e5409aee774c7ed29447cf80cc078/clip_encoder.py", line 46, in resize +2024-10-20 17:06:50 | ERROR | stderr | output_size = get_resize_output_image_size(image, size=(size["height"], size["width"]), default_to_square=True) +2024-10-20 17:06:50 | ERROR | stderr | KeyError: 'height' +2024-10-20 17:06:50 | INFO | httpx | HTTP Request: POST http://device-api.zero/release?allowToken=eebcff088cba1bb812d21b25bf8992a7ba76ffa043e56e0dacd24db4b6b0b4b2&fail=true "HTTP/1.1 200 OK" +2024-10-20 17:06:50 | ERROR | stderr | Traceback (most recent call last): +2024-10-20 17:06:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 703, in process_events +2024-10-20 17:06:50 | ERROR | stderr | response = await route_utils.call_process_api( +2024-10-20 17:06:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 323, in call_process_api +2024-10-20 17:06:50 | ERROR | stderr | output = await app.get_blocks().process_api( +2024-10-20 17:06:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2014, in process_api +2024-10-20 17:06:50 | ERROR | stderr | result = await self.call_function( +2024-10-20 17:06:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1579, in call_function +2024-10-20 17:06:50 | ERROR | stderr | prediction = await utils.async_iteration(iterator) +2024-10-20 17:06:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 691, in async_iteration +2024-10-20 17:06:50 | ERROR | stderr | return await anext(iterator) +2024-10-20 17:06:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 685, in __anext__ +2024-10-20 17:06:50 | ERROR | stderr | return await anyio.to_thread.run_sync( +2024-10-20 17:06:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync +2024-10-20 17:06:50 | ERROR | stderr | return await get_async_backend().run_sync_in_worker_thread( +2024-10-20 17:06:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2441, in run_sync_in_worker_thread +2024-10-20 17:06:50 | ERROR | stderr | return await future +2024-10-20 17:06:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 943, in run +2024-10-20 17:06:50 | ERROR | stderr | result = context.run(func, *args) +2024-10-20 17:06:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 668, in run_sync_iterator_async +2024-10-20 17:06:50 | ERROR | stderr | return next(iterator) +2024-10-20 17:06:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 829, in gen_wrapper +2024-10-20 17:06:50 | ERROR | stderr | response = next(iterator) +2024-10-20 17:06:50 | ERROR | stderr | File "/home/user/app/app.py", line 267, in http_bot +2024-10-20 17:06:50 | ERROR | stderr | extracted_texts = run_inference( +2024-10-20 17:06:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 214, in gradio_handler +2024-10-20 17:06:50 | ERROR | stderr | raise res.value +2024-10-20 17:06:50 | ERROR | stderr | KeyError: 'height' +2024-10-20 17:57:50 | INFO | stdout | conv mode to gemma +2024-10-20 17:57:50 | INFO | stdout | Input Image Size:(400, 433) +2024-10-20 17:57:50 | INFO | stdout | Input Image Size:(400, 433) +2024-10-20 17:57:50 | INFO | gradio_web_server | ==== request ==== +{'model': 'jadechoghari/Ferret-UI-Gemma2b', 'prompt': 'A chat between a human and an AI that understands visuals. In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. Increasing x moves right; y moves down. Bounding box: [x1, y1, x2, y2]. Image size: 1000x1000. Follow instructions.user\n\ndescribe the image in details\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['8b23f327b90b6211049acd36e3f99975']"} +2024-10-20 17:57:50 | INFO | stdout | Input Image Size:(400, 433) +2024-10-20 17:57:50 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=139933519567824&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NDM5OTMwfQ.IRQ7BAi6iGhKMiMxNEByAR74e_5B40KV0WuP_xa-Bsg "HTTP/1.1 429 Too Many Requests" +2024-10-20 17:57:50 | ERROR | stderr | Traceback (most recent call last): +2024-10-20 17:57:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 703, in process_events +2024-10-20 17:57:50 | ERROR | stderr | response = await route_utils.call_process_api( +2024-10-20 17:57:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 323, in call_process_api +2024-10-20 17:57:50 | ERROR | stderr | output = await app.get_blocks().process_api( +2024-10-20 17:57:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2014, in process_api +2024-10-20 17:57:50 | ERROR | stderr | result = await self.call_function( +2024-10-20 17:57:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1579, in call_function +2024-10-20 17:57:50 | ERROR | stderr | prediction = await utils.async_iteration(iterator) +2024-10-20 17:57:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 691, in async_iteration +2024-10-20 17:57:50 | ERROR | stderr | return await anext(iterator) +2024-10-20 17:57:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 685, in __anext__ +2024-10-20 17:57:50 | ERROR | stderr | return await anyio.to_thread.run_sync( +2024-10-20 17:57:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync +2024-10-20 17:57:50 | ERROR | stderr | return await get_async_backend().run_sync_in_worker_thread( +2024-10-20 17:57:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2441, in run_sync_in_worker_thread +2024-10-20 17:57:50 | ERROR | stderr | return await future +2024-10-20 17:57:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 943, in run +2024-10-20 17:57:50 | ERROR | stderr | result = context.run(func, *args) +2024-10-20 17:57:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 668, in run_sync_iterator_async +2024-10-20 17:57:50 | ERROR | stderr | return next(iterator) +2024-10-20 17:57:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 829, in gen_wrapper +2024-10-20 17:57:50 | ERROR | stderr | response = next(iterator) +2024-10-20 17:57:50 | ERROR | stderr | File "/home/user/app/app.py", line 267, in http_bot +2024-10-20 17:57:50 | ERROR | stderr | extracted_texts = run_inference( +2024-10-20 17:57:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 184, in gradio_handler +2024-10-20 17:57:50 | ERROR | stderr | schedule_response = client.schedule(task_id=task_id, request=request, duration=duration_) +2024-10-20 17:57:50 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/spaces/zero/client.py", line 139, in schedule +2024-10-20 17:57:50 | ERROR | stderr | raise HTMLError(html_string(message_html, message_text)) +2024-10-20 17:57:50 | ERROR | stderr | spaces.zero.gradio.HTMLError: You have exceeded your GPU quota (60s requested vs. 53s left). [Create a free account](https://huggingface.co/join) to get more usage quota. +2024-10-21 01:14:36 | INFO | stdout | conv mode to gemma +2024-10-21 01:14:36 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:14:36 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:14:36 | INFO | gradio_web_server | ==== request ==== +{'model': 'jadechoghari/Ferret-UI-Gemma2b', 'prompt': 'A chat between a human and an AI that understands visuals. In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. Increasing x moves right; y moves down. Bounding box: [x1, y1, x2, y2]. Image size: 1000x1000. Follow instructions.user\n\ndescribe what you see\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['8b23f327b90b6211049acd36e3f99975']"} +2024-10-21 01:14:36 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:14:36 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=139933519567824&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NDY2MTM2fQ.2g10JJWV-78W5nW60LzHAXzreanpi7wtkU6Ma64zQKw "HTTP/1.1 200 OK" +2024-10-21 01:14:36 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=18 +2024-10-21 01:14:36 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=21 +2024-10-21 01:14:36 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[15, 14, 16, 19, 10] +2024-10-21 01:14:37 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=d985548646b9805475ffa24e86374fab10acf32d4e17cf486f79a486c77bf9ec&pid=160207 "HTTP/1.1 200 OK" +2024-10-21 01:14:38 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 01:14:39 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 01:14:39 | ERROR | stderr | +2024-10-21 01:14:39 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00 +2024-10-21 01:14:46 | ERROR | stderr | image_patches = [processor.preprocess(image_patch, return_tensors='pt')['pixel_values'][0] +2024-10-21 01:14:46 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/transformers/models/clip/image_processing_clip.py", line 325, in preprocess +2024-10-21 01:14:46 | ERROR | stderr | image = self.resize(image=image, size=size, resample=resample, input_data_format=input_data_format) +2024-10-21 01:14:46 | ERROR | stderr | File "/home/user/.cache/huggingface/modules/transformers_modules/jadechoghari/Ferret-UI-Gemma2b/28bcebb3965e5409aee774c7ed29447cf80cc078/clip_encoder.py", line 46, in resize +2024-10-21 01:14:46 | ERROR | stderr | output_size = get_resize_output_image_size(image, size=(size["height"], size["width"]), default_to_square=True) +2024-10-21 01:14:46 | ERROR | stderr | KeyError: 'height' +2024-10-21 01:14:47 | INFO | httpx | HTTP Request: POST http://device-api.zero/release?allowToken=d985548646b9805475ffa24e86374fab10acf32d4e17cf486f79a486c77bf9ec&fail=true "HTTP/1.1 200 OK" +2024-10-21 01:14:47 | ERROR | stderr | Traceback (most recent call last): +2024-10-21 01:14:47 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 703, in process_events +2024-10-21 01:14:47 | ERROR | stderr | response = await route_utils.call_process_api( +2024-10-21 01:14:47 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 323, in call_process_api +2024-10-21 01:14:47 | ERROR | stderr | output = await app.get_blocks().process_api( +2024-10-21 01:14:47 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2014, in process_api +2024-10-21 01:14:47 | ERROR | stderr | result = await self.call_function( +2024-10-21 01:14:47 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1579, in call_function +2024-10-21 01:14:47 | ERROR | stderr | prediction = await utils.async_iteration(iterator) +2024-10-21 01:14:47 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 691, in async_iteration +2024-10-21 01:14:47 | ERROR | stderr | return await anext(iterator) +2024-10-21 01:14:47 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 685, in __anext__ +2024-10-21 01:14:47 | ERROR | stderr | return await anyio.to_thread.run_sync( +2024-10-21 01:14:47 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync +2024-10-21 01:14:47 | ERROR | stderr | return await get_async_backend().run_sync_in_worker_thread( +2024-10-21 01:14:47 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2441, in run_sync_in_worker_thread +2024-10-21 01:14:47 | ERROR | stderr | return await future +2024-10-21 01:14:47 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 943, in run +2024-10-21 01:14:47 | ERROR | stderr | result = context.run(func, *args) +2024-10-21 01:14:47 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 668, in run_sync_iterator_async +2024-10-21 01:14:47 | ERROR | stderr | return next(iterator) +2024-10-21 01:14:47 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 829, in gen_wrapper +2024-10-21 01:14:47 | ERROR | stderr | response = next(iterator) +2024-10-21 01:14:47 | ERROR | stderr | File "/home/user/app/app.py", line 267, in http_bot +2024-10-21 01:14:47 | ERROR | stderr | extracted_texts = run_inference( +2024-10-21 01:14:47 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 214, in gradio_handler +2024-10-21 01:14:47 | ERROR | stderr | raise res.value +2024-10-21 01:14:47 | ERROR | stderr | KeyError: 'height' +2024-10-21 01:24:49 | INFO | stdout | conv mode to gemma +2024-10-21 01:24:49 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:24:49 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:24:49 | INFO | gradio_web_server | ==== request ==== +{'model': 'jadechoghari/Ferret-UI-Gemma2b', 'prompt': 'A chat between a human and an AI that understands visuals. In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. Increasing x moves right; y moves down. Bounding box: [x1, y1, x2, y2]. Image size: 1000x1000. Follow instructions.user\n\ndescribe what you see\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['8b23f327b90b6211049acd36e3f99975']"} +2024-10-21 01:24:49 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:24:49 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=139933519567824&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NDY2NzQ5fQ.2ssJsOSfN0phT1hH0osxzbe7wA0vxZ4SCE6qvsaSiz4 "HTTP/1.1 200 OK" +2024-10-21 01:24:49 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=19 +2024-10-21 01:24:49 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=24 +2024-10-21 01:24:49 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[13, 14, 15, 16, 10] +2024-10-21 01:24:50 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=67e50667573a8e380e596840d7a7666c00fb65d7edd8d5217a7b7ffe092cea7a&pid=162033 "HTTP/1.1 200 OK" +2024-10-21 01:24:51 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 01:24:52 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 01:24:52 | ERROR | stderr | +2024-10-21 01:24:52 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00 +2024-10-21 01:24:58 | ERROR | stderr | image_patches = [processor.preprocess(image_patch, return_tensors='pt')['pixel_values'][0] +2024-10-21 01:24:58 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/transformers/models/clip/image_processing_clip.py", line 325, in preprocess +2024-10-21 01:24:58 | ERROR | stderr | image = self.resize(image=image, size=size, resample=resample, input_data_format=input_data_format) +2024-10-21 01:24:58 | ERROR | stderr | File "/home/user/.cache/huggingface/modules/transformers_modules/jadechoghari/Ferret-UI-Gemma2b/28bcebb3965e5409aee774c7ed29447cf80cc078/clip_encoder.py", line 46, in resize +2024-10-21 01:24:58 | ERROR | stderr | output_size = get_resize_output_image_size(image, size=(size["height"], size["width"]), default_to_square=True) +2024-10-21 01:24:58 | ERROR | stderr | KeyError: 'height' +2024-10-21 01:24:58 | INFO | httpx | HTTP Request: POST http://device-api.zero/release?allowToken=67e50667573a8e380e596840d7a7666c00fb65d7edd8d5217a7b7ffe092cea7a&fail=true "HTTP/1.1 200 OK" +2024-10-21 01:24:58 | ERROR | stderr | Traceback (most recent call last): +2024-10-21 01:24:58 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 703, in process_events +2024-10-21 01:24:58 | ERROR | stderr | response = await route_utils.call_process_api( +2024-10-21 01:24:58 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 323, in call_process_api +2024-10-21 01:24:58 | ERROR | stderr | output = await app.get_blocks().process_api( +2024-10-21 01:24:58 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2014, in process_api +2024-10-21 01:24:58 | ERROR | stderr | result = await self.call_function( +2024-10-21 01:24:58 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1579, in call_function +2024-10-21 01:24:58 | ERROR | stderr | prediction = await utils.async_iteration(iterator) +2024-10-21 01:24:58 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 691, in async_iteration +2024-10-21 01:24:58 | ERROR | stderr | return await anext(iterator) +2024-10-21 01:24:58 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 685, in __anext__ +2024-10-21 01:24:58 | ERROR | stderr | return await anyio.to_thread.run_sync( +2024-10-21 01:24:58 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync +2024-10-21 01:24:58 | ERROR | stderr | return await get_async_backend().run_sync_in_worker_thread( +2024-10-21 01:24:58 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2441, in run_sync_in_worker_thread +2024-10-21 01:24:58 | ERROR | stderr | return await future +2024-10-21 01:24:58 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 943, in run +2024-10-21 01:24:58 | ERROR | stderr | result = context.run(func, *args) +2024-10-21 01:24:58 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 668, in run_sync_iterator_async +2024-10-21 01:24:58 | ERROR | stderr | return next(iterator) +2024-10-21 01:24:58 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 829, in gen_wrapper +2024-10-21 01:24:58 | ERROR | stderr | response = next(iterator) +2024-10-21 01:24:58 | ERROR | stderr | File "/home/user/app/app.py", line 267, in http_bot +2024-10-21 01:24:58 | ERROR | stderr | extracted_texts = run_inference( +2024-10-21 01:24:58 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 214, in gradio_handler +2024-10-21 01:24:58 | ERROR | stderr | raise res.value +2024-10-21 01:24:58 | ERROR | stderr | KeyError: 'height' +2024-10-21 01:27:12 | INFO | gradio_web_server | args: Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-21 01:27:12 | INFO | gradio_web_server | Models: ['jadechoghari/Ferret-UI-Gemma2b'] +2024-10-21 01:27:12 | INFO | gradio_web_server | Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-21 01:27:12 | ERROR | stderr | /usr/local/lib/python3.10/site-packages/gradio/components/chatbot.py:222: UserWarning: You have not specified a value for the `type` parameter. Defaulting to the 'tuples' format for chatbot messages, but this is deprecated and will be removed in a future version of Gradio. Please set type='messages' instead, which uses openai-style 'role' and 'content' keys. +2024-10-21 01:27:12 | ERROR | stderr | warnings.warn( +2024-10-21 01:27:12 | ERROR | stderr | +2024-10-21 01:27:12 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-21 01:27:12 | ERROR | stderr |  +2024-10-21 01:27:12 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-21 01:27:12 | ERROR | stderr | +2024-10-21 01:27:12 | INFO | httpx | HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK" +2024-10-21 01:27:12 | INFO | stdout | Cannot start Node server on any port in the range 7861-7861. +2024-10-21 01:27:12 | INFO | stdout | Please install Node 20 or higher and set the environment variable GRADIO_NODE_PATH to the path of your Node executable. +2024-10-21 01:27:12 | INFO | stdout | You can explicitly specify a port by setting the environment variable GRADIO_NODE_PORT. +2024-10-21 01:27:12 | INFO | stdout | * Running on local URL: http://0.0.0.0:7860, with SSR ⚡ +2024-10-21 01:27:12 | INFO | httpx | HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK" +2024-10-21 01:27:12 | INFO | httpx | HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK" +2024-10-21 01:27:12 | ERROR | stderr | /usr/local/lib/python3.10/site-packages/gradio/blocks.py:2595: UserWarning: Setting share=True is not supported on Hugging Face Spaces +2024-10-21 01:27:12 | ERROR | stderr | warnings.warn( +2024-10-21 01:27:12 | INFO | stdout | +2024-10-21 01:27:12 | INFO | stdout | To create a public link, set `share=True` in `launch()`. +2024-10-21 01:27:39 | INFO | gradio_web_server | args: Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-21 01:27:39 | INFO | gradio_web_server | Models: ['jadechoghari/Ferret-UI-Gemma2b'] +2024-10-21 01:27:39 | INFO | gradio_web_server | Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-21 01:27:39 | ERROR | stderr | /usr/local/lib/python3.10/site-packages/gradio/components/chatbot.py:222: UserWarning: You have not specified a value for the `type` parameter. Defaulting to the 'tuples' format for chatbot messages, but this is deprecated and will be removed in a future version of Gradio. Please set type='messages' instead, which uses openai-style 'role' and 'content' keys. +2024-10-21 01:27:39 | ERROR | stderr | warnings.warn( +2024-10-21 01:27:39 | ERROR | stderr | +2024-10-21 01:27:39 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-21 01:27:39 | ERROR | stderr |  +2024-10-21 01:27:39 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-21 01:27:39 | ERROR | stderr | +2024-10-21 01:27:39 | INFO | stdout | Cannot start Node server on any port in the range 7861-7861. +2024-10-21 01:27:39 | INFO | stdout | Please install Node 20 or higher and set the environment variable GRADIO_NODE_PATH to the path of your Node executable. +2024-10-21 01:27:39 | INFO | stdout | You can explicitly specify a port by setting the environment variable GRADIO_NODE_PORT. +2024-10-21 01:27:39 | INFO | httpx | HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK" +2024-10-21 01:27:39 | INFO | stdout | * Running on local URL: http://0.0.0.0:7860, with SSR ⚡ +2024-10-21 01:27:39 | INFO | httpx | HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK" +2024-10-21 01:27:39 | INFO | httpx | HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK" +2024-10-21 01:27:39 | ERROR | stderr | /usr/local/lib/python3.10/site-packages/gradio/blocks.py:2595: UserWarning: Setting share=True is not supported on Hugging Face Spaces +2024-10-21 01:27:39 | ERROR | stderr | warnings.warn( +2024-10-21 01:27:39 | INFO | stdout | +2024-10-21 01:27:39 | INFO | stdout | To create a public link, set `share=True` in `launch()`. +2024-10-21 01:27:52 | INFO | stdout | conv mode to gemma +2024-10-21 01:27:52 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:27:52 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:27:52 | INFO | gradio_web_server | ==== request ==== +{'model': 'jadechoghari/Ferret-UI-Gemma2b', 'prompt': 'A chat between a human and an AI that understands visuals. In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. Increasing x moves right; y moves down. Bounding box: [x1, y1, x2, y2]. Image size: 1000x1000. Follow instructions.user\n\ndescribe what you see in details\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['8b23f327b90b6211049acd36e3f99975']"} +2024-10-21 01:27:52 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:27:52 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=140484646902736&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NDY2OTMyfQ.XfZ2mQRJU-hWhsJbLaGPgawhklB0rySqTHX0o5tbuA4 "HTTP/1.1 200 OK" +2024-10-21 01:27:52 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=18 +2024-10-21 01:27:52 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=20 +2024-10-21 01:27:52 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[16, 14, 13, 10] +2024-10-21 01:27:52 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=f51e510aa3aee8f0ee7636868ee07d841e5d18ed79f61cecb119fe9293bda42b&pid=163170 "HTTP/1.1 200 OK" +2024-10-21 01:27:54 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 01:27:55 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 01:27:55 | ERROR | stderr | +2024-10-21 01:27:55 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00 +2024-10-21 01:28:00 | ERROR | stderr | image_patches = [processor.preprocess(image_patch, return_tensors='pt')['pixel_values'][0] +2024-10-21 01:28:00 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/transformers/models/clip/image_processing_clip.py", line 325, in preprocess +2024-10-21 01:28:00 | ERROR | stderr | image = self.resize(image=image, size=size, resample=resample, input_data_format=input_data_format) +2024-10-21 01:28:00 | ERROR | stderr | File "/home/user/.cache/huggingface/modules/transformers_modules/jadechoghari/Ferret-UI-Gemma2b/28bcebb3965e5409aee774c7ed29447cf80cc078/clip_encoder.py", line 46, in resize +2024-10-21 01:28:00 | ERROR | stderr | output_size = get_resize_output_image_size(image, size=(size["height"], size["width"]), default_to_square=True) +2024-10-21 01:28:00 | ERROR | stderr | KeyError: 'height' +2024-10-21 01:28:01 | INFO | httpx | HTTP Request: POST http://device-api.zero/release?allowToken=f51e510aa3aee8f0ee7636868ee07d841e5d18ed79f61cecb119fe9293bda42b&fail=true "HTTP/1.1 200 OK" +2024-10-21 01:28:01 | ERROR | stderr | Traceback (most recent call last): +2024-10-21 01:28:01 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 703, in process_events +2024-10-21 01:28:01 | ERROR | stderr | response = await route_utils.call_process_api( +2024-10-21 01:28:01 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 323, in call_process_api +2024-10-21 01:28:01 | ERROR | stderr | output = await app.get_blocks().process_api( +2024-10-21 01:28:01 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2014, in process_api +2024-10-21 01:28:01 | ERROR | stderr | result = await self.call_function( +2024-10-21 01:28:01 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1579, in call_function +2024-10-21 01:28:01 | ERROR | stderr | prediction = await utils.async_iteration(iterator) +2024-10-21 01:28:01 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 691, in async_iteration +2024-10-21 01:28:01 | ERROR | stderr | return await anext(iterator) +2024-10-21 01:28:01 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 685, in __anext__ +2024-10-21 01:28:01 | ERROR | stderr | return await anyio.to_thread.run_sync( +2024-10-21 01:28:01 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync +2024-10-21 01:28:01 | ERROR | stderr | return await get_async_backend().run_sync_in_worker_thread( +2024-10-21 01:28:01 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2441, in run_sync_in_worker_thread +2024-10-21 01:28:01 | ERROR | stderr | return await future +2024-10-21 01:28:01 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 943, in run +2024-10-21 01:28:01 | ERROR | stderr | result = context.run(func, *args) +2024-10-21 01:28:01 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 668, in run_sync_iterator_async +2024-10-21 01:28:01 | ERROR | stderr | return next(iterator) +2024-10-21 01:28:01 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 829, in gen_wrapper +2024-10-21 01:28:01 | ERROR | stderr | response = next(iterator) +2024-10-21 01:28:01 | ERROR | stderr | File "/home/user/app/app.py", line 267, in http_bot +2024-10-21 01:28:01 | ERROR | stderr | extracted_texts = run_inference( +2024-10-21 01:28:01 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 214, in gradio_handler +2024-10-21 01:28:01 | ERROR | stderr | raise res.value +2024-10-21 01:28:01 | ERROR | stderr | KeyError: 'height' +2024-10-21 01:39:20 | INFO | stdout | conv mode to gemma +2024-10-21 01:39:20 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:39:20 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:39:20 | INFO | gradio_web_server | ==== request ==== +{'model': 'jadechoghari/Ferret-UI-Gemma2b', 'prompt': 'A chat between a human and an AI that understands visuals. In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. Increasing x moves right; y moves down. Bounding box: [x1, y1, x2, y2]. Image size: 1000x1000. Follow instructions.user\n\ndescribe this image in details\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['8b23f327b90b6211049acd36e3f99975']"} +2024-10-21 01:39:20 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:39:21 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=140484646902736&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NDY3NjIwfQ.tAxO0nJUGqCV7JjLSXY-Vlo0jYXDAuYNocD2hU9TYfg "HTTP/1.1 200 OK" +2024-10-21 01:39:21 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=18 +2024-10-21 01:39:21 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=23 +2024-10-21 01:39:21 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[15, 13, 10, 14] +2024-10-21 01:39:21 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=c962eb316deaad0301ee35670b454772cb1690c2f4297d0737fbdbd5679b253f&pid=166096 "HTTP/1.1 200 OK" +2024-10-21 01:39:22 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 01:39:24 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 01:39:24 | ERROR | stderr | +2024-10-21 01:39:24 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00 +2024-10-21 01:39:31 | ERROR | stderr | image_patches = [processor.preprocess(image_patch, return_tensors='pt')['pixel_values'][0] +2024-10-21 01:39:31 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/transformers/models/clip/image_processing_clip.py", line 325, in preprocess +2024-10-21 01:39:31 | ERROR | stderr | image = self.resize(image=image, size=size, resample=resample, input_data_format=input_data_format) +2024-10-21 01:39:31 | ERROR | stderr | File "/home/user/.cache/huggingface/modules/transformers_modules/jadechoghari/Ferret-UI-Gemma2b/28bcebb3965e5409aee774c7ed29447cf80cc078/clip_encoder.py", line 46, in resize +2024-10-21 01:39:31 | ERROR | stderr | output_size = get_resize_output_image_size(image, size=(size["height"], size["width"]), default_to_square=True) +2024-10-21 01:39:31 | ERROR | stderr | KeyError: 'height' +2024-10-21 01:39:31 | INFO | httpx | HTTP Request: POST http://device-api.zero/release?allowToken=c962eb316deaad0301ee35670b454772cb1690c2f4297d0737fbdbd5679b253f&fail=true "HTTP/1.1 200 OK" +2024-10-21 01:39:31 | ERROR | stderr | Traceback (most recent call last): +2024-10-21 01:39:31 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 703, in process_events +2024-10-21 01:39:31 | ERROR | stderr | response = await route_utils.call_process_api( +2024-10-21 01:39:31 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 323, in call_process_api +2024-10-21 01:39:31 | ERROR | stderr | output = await app.get_blocks().process_api( +2024-10-21 01:39:31 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2014, in process_api +2024-10-21 01:39:31 | ERROR | stderr | result = await self.call_function( +2024-10-21 01:39:31 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1579, in call_function +2024-10-21 01:39:31 | ERROR | stderr | prediction = await utils.async_iteration(iterator) +2024-10-21 01:39:31 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 691, in async_iteration +2024-10-21 01:39:31 | ERROR | stderr | return await anext(iterator) +2024-10-21 01:39:31 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 685, in __anext__ +2024-10-21 01:39:31 | ERROR | stderr | return await anyio.to_thread.run_sync( +2024-10-21 01:39:31 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync +2024-10-21 01:39:31 | ERROR | stderr | return await get_async_backend().run_sync_in_worker_thread( +2024-10-21 01:39:31 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2441, in run_sync_in_worker_thread +2024-10-21 01:39:31 | ERROR | stderr | return await future +2024-10-21 01:39:31 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 943, in run +2024-10-21 01:39:31 | ERROR | stderr | result = context.run(func, *args) +2024-10-21 01:39:31 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 668, in run_sync_iterator_async +2024-10-21 01:39:31 | ERROR | stderr | return next(iterator) +2024-10-21 01:39:31 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 829, in gen_wrapper +2024-10-21 01:39:31 | ERROR | stderr | response = next(iterator) +2024-10-21 01:39:31 | ERROR | stderr | File "/home/user/app/app.py", line 267, in http_bot +2024-10-21 01:39:31 | ERROR | stderr | extracted_texts = run_inference( +2024-10-21 01:39:31 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 214, in gradio_handler +2024-10-21 01:39:31 | ERROR | stderr | raise res.value +2024-10-21 01:39:31 | ERROR | stderr | KeyError: 'height' +2024-10-21 01:40:56 | INFO | gradio_web_server | args: Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-21 01:40:56 | INFO | gradio_web_server | Models: ['jadechoghari/Ferret-UI-Gemma2b'] +2024-10-21 01:40:56 | INFO | gradio_web_server | Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-21 01:40:56 | ERROR | stderr | /usr/local/lib/python3.10/site-packages/gradio/components/chatbot.py:222: UserWarning: You have not specified a value for the `type` parameter. Defaulting to the 'tuples' format for chatbot messages, but this is deprecated and will be removed in a future version of Gradio. Please set type='messages' instead, which uses openai-style 'role' and 'content' keys. +2024-10-21 01:40:56 | ERROR | stderr | warnings.warn( +2024-10-21 01:40:56 | ERROR | stderr | +2024-10-21 01:40:56 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-21 01:40:56 | ERROR | stderr |  +2024-10-21 01:40:56 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-21 01:40:56 | ERROR | stderr | +2024-10-21 01:40:56 | INFO | httpx | HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK" +2024-10-21 01:40:56 | INFO | stdout | Cannot start Node server on any port in the range 7861-7861. +2024-10-21 01:40:56 | INFO | stdout | Please install Node 20 or higher and set the environment variable GRADIO_NODE_PATH to the path of your Node executable. +2024-10-21 01:40:56 | INFO | stdout | You can explicitly specify a port by setting the environment variable GRADIO_NODE_PORT. +2024-10-21 01:40:56 | INFO | stdout | * Running on local URL: http://0.0.0.0:7860, with SSR ⚡ +2024-10-21 01:40:56 | INFO | httpx | HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK" +2024-10-21 01:40:56 | INFO | httpx | HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK" +2024-10-21 01:40:56 | ERROR | stderr | /usr/local/lib/python3.10/site-packages/gradio/blocks.py:2595: UserWarning: Setting share=True is not supported on Hugging Face Spaces +2024-10-21 01:40:56 | ERROR | stderr | warnings.warn( +2024-10-21 01:40:56 | INFO | stdout | +2024-10-21 01:40:56 | INFO | stdout | To create a public link, set `share=True` in `launch()`. +2024-10-21 01:41:11 | INFO | stdout | conv mode to gemma +2024-10-21 01:41:11 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:41:11 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:41:11 | INFO | gradio_web_server | ==== request ==== +{'model': 'jadechoghari/Ferret-UI-Gemma2b', 'prompt': 'A chat between a human and an AI that understands visuals. In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. Increasing x moves right; y moves down. Bounding box: [x1, y1, x2, y2]. Image size: 1000x1000. Follow instructions.user\n\ndescribe what you see in details\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['8b23f327b90b6211049acd36e3f99975']"} +2024-10-21 01:41:11 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:41:11 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=139635038215120&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NDY3NzMxfQ.8m7arMitMiWUAAvl0526BSo8wYnUnLtdB_ff7w3P6QM "HTTP/1.1 200 OK" +2024-10-21 01:41:11 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=19 +2024-10-21 01:41:11 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=21 +2024-10-21 01:41:11 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[10, 16, 15, 13, 14] +2024-10-21 01:41:12 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=552fbe44ffe57440a8f180bcb3db2bc2e033bff1bfc41fd698f0d97fea3d2f77&pid=166804 "HTTP/1.1 200 OK" +2024-10-21 01:41:13 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 01:41:14 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 01:41:14 | ERROR | stderr | +2024-10-21 01:41:14 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00 +2024-10-21 01:41:22 | ERROR | stderr | image_patches = [processor.preprocess(image_patch, return_tensors='pt')['pixel_values'][0] +2024-10-21 01:41:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/transformers/models/clip/image_processing_clip.py", line 325, in preprocess +2024-10-21 01:41:22 | ERROR | stderr | image = self.resize(image=image, size=size, resample=resample, input_data_format=input_data_format) +2024-10-21 01:41:22 | ERROR | stderr | File "/home/user/.cache/huggingface/modules/transformers_modules/jadechoghari/Ferret-UI-Gemma2b/28bcebb3965e5409aee774c7ed29447cf80cc078/clip_encoder.py", line 46, in resize +2024-10-21 01:41:22 | ERROR | stderr | output_size = get_resize_output_image_size(image, size=(size["height"], size["width"]), default_to_square=True) +2024-10-21 01:41:22 | ERROR | stderr | KeyError: 'height' +2024-10-21 01:41:22 | INFO | httpx | HTTP Request: POST http://device-api.zero/release?allowToken=552fbe44ffe57440a8f180bcb3db2bc2e033bff1bfc41fd698f0d97fea3d2f77&fail=true "HTTP/1.1 200 OK" +2024-10-21 01:41:22 | ERROR | stderr | Traceback (most recent call last): +2024-10-21 01:41:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 703, in process_events +2024-10-21 01:41:22 | ERROR | stderr | response = await route_utils.call_process_api( +2024-10-21 01:41:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 323, in call_process_api +2024-10-21 01:41:22 | ERROR | stderr | output = await app.get_blocks().process_api( +2024-10-21 01:41:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2014, in process_api +2024-10-21 01:41:22 | ERROR | stderr | result = await self.call_function( +2024-10-21 01:41:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1579, in call_function +2024-10-21 01:41:22 | ERROR | stderr | prediction = await utils.async_iteration(iterator) +2024-10-21 01:41:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 691, in async_iteration +2024-10-21 01:41:22 | ERROR | stderr | return await anext(iterator) +2024-10-21 01:41:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 685, in __anext__ +2024-10-21 01:41:22 | ERROR | stderr | return await anyio.to_thread.run_sync( +2024-10-21 01:41:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync +2024-10-21 01:41:22 | ERROR | stderr | return await get_async_backend().run_sync_in_worker_thread( +2024-10-21 01:41:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2441, in run_sync_in_worker_thread +2024-10-21 01:41:22 | ERROR | stderr | return await future +2024-10-21 01:41:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 943, in run +2024-10-21 01:41:22 | ERROR | stderr | result = context.run(func, *args) +2024-10-21 01:41:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 668, in run_sync_iterator_async +2024-10-21 01:41:22 | ERROR | stderr | return next(iterator) +2024-10-21 01:41:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 829, in gen_wrapper +2024-10-21 01:41:22 | ERROR | stderr | response = next(iterator) +2024-10-21 01:41:22 | ERROR | stderr | File "/home/user/app/app.py", line 267, in http_bot +2024-10-21 01:41:22 | ERROR | stderr | extracted_texts = run_inference( +2024-10-21 01:41:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 214, in gradio_handler +2024-10-21 01:41:22 | ERROR | stderr | raise res.value +2024-10-21 01:41:22 | ERROR | stderr | KeyError: 'height' +2024-10-21 01:44:04 | INFO | stdout | conv mode to gemma +2024-10-21 01:44:04 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:44:04 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:44:04 | INFO | gradio_web_server | ==== request ==== +{'model': 'jadechoghari/Ferret-UI-Gemma2b', 'prompt': 'A chat between a human and an AI that understands visuals. In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. Increasing x moves right; y moves down. Bounding box: [x1, y1, x2, y2]. Image size: 1000x1000. Follow instructions.user\n\ndescribe what you see in details\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['8b23f327b90b6211049acd36e3f99975']"} +2024-10-21 01:44:04 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:44:04 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=139635038215120&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NDY3OTA0fQ.OlWC49UJZeLljZp9t2vbd1Tjuedoqsm3EYcXGSQIAVY "HTTP/1.1 200 OK" +2024-10-21 01:44:04 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=19 +2024-10-21 01:44:04 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=21 +2024-10-21 01:44:04 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[10, 13, 15, 16, 14] +2024-10-21 01:44:04 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=447a22764433297b5724435eb0fd8b9ea8bb2bdaf7f30e34d648d0a0e56deebc&pid=167522 "HTTP/1.1 200 OK" +2024-10-21 01:44:05 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 01:44:07 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 01:44:07 | ERROR | stderr | +2024-10-21 01:44:07 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00 +2024-10-21 01:44:13 | ERROR | stderr | image_patches = [processor.preprocess(image_patch, return_tensors='pt')['pixel_values'][0] +2024-10-21 01:44:13 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/transformers/models/clip/image_processing_clip.py", line 325, in preprocess +2024-10-21 01:44:13 | ERROR | stderr | image = self.resize(image=image, size=size, resample=resample, input_data_format=input_data_format) +2024-10-21 01:44:13 | ERROR | stderr | File "/home/user/.cache/huggingface/modules/transformers_modules/jadechoghari/Ferret-UI-Gemma2b/28bcebb3965e5409aee774c7ed29447cf80cc078/clip_encoder.py", line 46, in resize +2024-10-21 01:44:13 | ERROR | stderr | output_size = get_resize_output_image_size(image, size=(size["height"], size["width"]), default_to_square=True) +2024-10-21 01:44:13 | ERROR | stderr | KeyError: 'height' +2024-10-21 01:44:13 | INFO | httpx | HTTP Request: POST http://device-api.zero/release?allowToken=447a22764433297b5724435eb0fd8b9ea8bb2bdaf7f30e34d648d0a0e56deebc&fail=true "HTTP/1.1 200 OK" +2024-10-21 01:44:13 | ERROR | stderr | Traceback (most recent call last): +2024-10-21 01:44:13 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 703, in process_events +2024-10-21 01:44:13 | ERROR | stderr | response = await route_utils.call_process_api( +2024-10-21 01:44:13 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 323, in call_process_api +2024-10-21 01:44:13 | ERROR | stderr | output = await app.get_blocks().process_api( +2024-10-21 01:44:13 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2014, in process_api +2024-10-21 01:44:13 | ERROR | stderr | result = await self.call_function( +2024-10-21 01:44:13 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1579, in call_function +2024-10-21 01:44:13 | ERROR | stderr | prediction = await utils.async_iteration(iterator) +2024-10-21 01:44:13 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 691, in async_iteration +2024-10-21 01:44:13 | ERROR | stderr | return await anext(iterator) +2024-10-21 01:44:13 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 685, in __anext__ +2024-10-21 01:44:13 | ERROR | stderr | return await anyio.to_thread.run_sync( +2024-10-21 01:44:13 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync +2024-10-21 01:44:13 | ERROR | stderr | return await get_async_backend().run_sync_in_worker_thread( +2024-10-21 01:44:13 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2441, in run_sync_in_worker_thread +2024-10-21 01:44:13 | ERROR | stderr | return await future +2024-10-21 01:44:13 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 943, in run +2024-10-21 01:44:13 | ERROR | stderr | result = context.run(func, *args) +2024-10-21 01:44:13 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 668, in run_sync_iterator_async +2024-10-21 01:44:13 | ERROR | stderr | return next(iterator) +2024-10-21 01:44:13 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 829, in gen_wrapper +2024-10-21 01:44:13 | ERROR | stderr | response = next(iterator) +2024-10-21 01:44:13 | ERROR | stderr | File "/home/user/app/app.py", line 267, in http_bot +2024-10-21 01:44:13 | ERROR | stderr | extracted_texts = run_inference( +2024-10-21 01:44:13 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 214, in gradio_handler +2024-10-21 01:44:13 | ERROR | stderr | raise res.value +2024-10-21 01:44:13 | ERROR | stderr | KeyError: 'height' +2024-10-21 01:47:19 | INFO | gradio_web_server | args: Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-21 01:47:19 | INFO | gradio_web_server | Models: ['jadechoghari/Ferret-UI-Gemma2b'] +2024-10-21 01:47:19 | INFO | gradio_web_server | Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-21 01:47:19 | ERROR | stderr | /usr/local/lib/python3.10/site-packages/gradio/components/chatbot.py:222: UserWarning: You have not specified a value for the `type` parameter. Defaulting to the 'tuples' format for chatbot messages, but this is deprecated and will be removed in a future version of Gradio. Please set type='messages' instead, which uses openai-style 'role' and 'content' keys. +2024-10-21 01:47:19 | ERROR | stderr | warnings.warn( +2024-10-21 01:47:19 | ERROR | stderr | +2024-10-21 01:47:19 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-21 01:47:19 | ERROR | stderr |  +2024-10-21 01:47:19 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-21 01:47:19 | ERROR | stderr | +2024-10-21 01:47:19 | INFO | httpx | HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK" +2024-10-21 01:47:19 | INFO | stdout | Cannot start Node server on any port in the range 7861-7861. +2024-10-21 01:47:19 | INFO | stdout | Please install Node 20 or higher and set the environment variable GRADIO_NODE_PATH to the path of your Node executable. +2024-10-21 01:47:19 | INFO | stdout | You can explicitly specify a port by setting the environment variable GRADIO_NODE_PORT. +2024-10-21 01:47:19 | INFO | stdout | * Running on local URL: http://0.0.0.0:7860, with SSR ⚡ +2024-10-21 01:47:19 | INFO | httpx | HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK" +2024-10-21 01:47:19 | INFO | httpx | HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK" +2024-10-21 01:47:19 | ERROR | stderr | /usr/local/lib/python3.10/site-packages/gradio/blocks.py:2595: UserWarning: Setting share=True is not supported on Hugging Face Spaces +2024-10-21 01:47:19 | ERROR | stderr | warnings.warn( +2024-10-21 01:47:19 | INFO | stdout | +2024-10-21 01:47:19 | INFO | stdout | To create a public link, set `share=True` in `launch()`. +2024-10-21 01:47:32 | INFO | stdout | conv mode to gemma +2024-10-21 01:47:32 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:47:32 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:47:32 | INFO | gradio_web_server | ==== request ==== +{'model': 'jadechoghari/Ferret-UI-Gemma2b', 'prompt': 'A chat between a human and an AI that understands visuals. In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. Increasing x moves right; y moves down. Bounding box: [x1, y1, x2, y2]. Image size: 1000x1000. Follow instructions.user\n\ndescribe the image in details\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['8b23f327b90b6211049acd36e3f99975']"} +2024-10-21 01:47:32 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:47:32 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=140604188695504&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NDY4MTEyfQ.fVhFDQ-Vo0yO9XF0BbZi6MXymo4PrMqyoSJfI-fVQyY "HTTP/1.1 200 OK" +2024-10-21 01:47:32 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=19 +2024-10-21 01:47:32 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=21 +2024-10-21 01:47:32 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[14, 10, 13, 16, 15] +2024-10-21 01:47:33 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=07e619fad2c683e5e78c722a5e135248587eeb0d294bb4f3f6793cfe8ab3621f&pid=168612 "HTTP/1.1 200 OK" +2024-10-21 01:47:34 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 01:47:36 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 01:47:36 | ERROR | stderr | +2024-10-21 01:47:36 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00 +2024-10-21 01:47:42 | ERROR | stderr | image_patches = [processor.preprocess(image_patch, return_tensors='pt')['pixel_values'][0] +2024-10-21 01:47:42 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/transformers/models/clip/image_processing_clip.py", line 325, in preprocess +2024-10-21 01:47:42 | ERROR | stderr | image = self.resize(image=image, size=size, resample=resample, input_data_format=input_data_format) +2024-10-21 01:47:42 | ERROR | stderr | File "/home/user/.cache/huggingface/modules/transformers_modules/jadechoghari/Ferret-UI-Gemma2b/28bcebb3965e5409aee774c7ed29447cf80cc078/clip_encoder.py", line 46, in resize +2024-10-21 01:47:42 | ERROR | stderr | output_size = get_resize_output_image_size(image, size=(size["height"], size["width"]), default_to_square=True) +2024-10-21 01:47:42 | ERROR | stderr | KeyError: 'height' +2024-10-21 01:47:42 | INFO | httpx | HTTP Request: POST http://device-api.zero/release?allowToken=07e619fad2c683e5e78c722a5e135248587eeb0d294bb4f3f6793cfe8ab3621f&fail=true "HTTP/1.1 200 OK" +2024-10-21 01:47:42 | ERROR | stderr | Traceback (most recent call last): +2024-10-21 01:47:42 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 703, in process_events +2024-10-21 01:47:42 | ERROR | stderr | response = await route_utils.call_process_api( +2024-10-21 01:47:42 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 323, in call_process_api +2024-10-21 01:47:42 | ERROR | stderr | output = await app.get_blocks().process_api( +2024-10-21 01:47:42 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2014, in process_api +2024-10-21 01:47:42 | ERROR | stderr | result = await self.call_function( +2024-10-21 01:47:42 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1579, in call_function +2024-10-21 01:47:42 | ERROR | stderr | prediction = await utils.async_iteration(iterator) +2024-10-21 01:47:42 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 691, in async_iteration +2024-10-21 01:47:42 | ERROR | stderr | return await anext(iterator) +2024-10-21 01:47:42 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 685, in __anext__ +2024-10-21 01:47:42 | ERROR | stderr | return await anyio.to_thread.run_sync( +2024-10-21 01:47:42 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync +2024-10-21 01:47:42 | ERROR | stderr | return await get_async_backend().run_sync_in_worker_thread( +2024-10-21 01:47:42 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2441, in run_sync_in_worker_thread +2024-10-21 01:47:42 | ERROR | stderr | return await future +2024-10-21 01:47:42 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 943, in run +2024-10-21 01:47:42 | ERROR | stderr | result = context.run(func, *args) +2024-10-21 01:47:42 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 668, in run_sync_iterator_async +2024-10-21 01:47:42 | ERROR | stderr | return next(iterator) +2024-10-21 01:47:42 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 829, in gen_wrapper +2024-10-21 01:47:42 | ERROR | stderr | response = next(iterator) +2024-10-21 01:47:42 | ERROR | stderr | File "/home/user/app/app.py", line 267, in http_bot +2024-10-21 01:47:42 | ERROR | stderr | extracted_texts = run_inference( +2024-10-21 01:47:42 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 214, in gradio_handler +2024-10-21 01:47:42 | ERROR | stderr | raise res.value +2024-10-21 01:47:42 | ERROR | stderr | KeyError: 'height' +2024-10-21 01:49:24 | INFO | gradio_web_server | args: Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-21 01:49:24 | INFO | gradio_web_server | Models: ['jadechoghari/Ferret-UI-Gemma2b'] +2024-10-21 01:49:24 | INFO | gradio_web_server | Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-21 01:49:25 | ERROR | stderr | /usr/local/lib/python3.10/site-packages/gradio/components/chatbot.py:222: UserWarning: You have not specified a value for the `type` parameter. Defaulting to the 'tuples' format for chatbot messages, but this is deprecated and will be removed in a future version of Gradio. Please set type='messages' instead, which uses openai-style 'role' and 'content' keys. +2024-10-21 01:49:25 | ERROR | stderr | warnings.warn( +2024-10-21 01:49:25 | ERROR | stderr | +2024-10-21 01:49:25 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-21 01:49:25 | ERROR | stderr |  +2024-10-21 01:49:25 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-21 01:49:25 | ERROR | stderr | +2024-10-21 01:49:25 | INFO | httpx | HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK" +2024-10-21 01:49:25 | INFO | stdout | Cannot start Node server on any port in the range 7861-7861. +2024-10-21 01:49:25 | INFO | stdout | Please install Node 20 or higher and set the environment variable GRADIO_NODE_PATH to the path of your Node executable. +2024-10-21 01:49:25 | INFO | stdout | You can explicitly specify a port by setting the environment variable GRADIO_NODE_PORT. +2024-10-21 01:49:25 | INFO | stdout | * Running on local URL: http://0.0.0.0:7860, with SSR ⚡ +2024-10-21 01:49:25 | INFO | httpx | HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK" +2024-10-21 01:49:25 | INFO | httpx | HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK" +2024-10-21 01:49:25 | ERROR | stderr | /usr/local/lib/python3.10/site-packages/gradio/blocks.py:2595: UserWarning: Setting share=True is not supported on Hugging Face Spaces +2024-10-21 01:49:25 | ERROR | stderr | warnings.warn( +2024-10-21 01:49:25 | INFO | stdout | +2024-10-21 01:49:25 | INFO | stdout | To create a public link, set `share=True` in `launch()`. +2024-10-21 01:51:38 | INFO | gradio_web_server | args: Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-21 01:51:38 | INFO | gradio_web_server | Models: ['jadechoghari/Ferret-UI-Gemma2b'] +2024-10-21 01:51:38 | INFO | gradio_web_server | Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-21 01:51:38 | ERROR | stderr | /usr/local/lib/python3.10/site-packages/gradio/components/chatbot.py:222: UserWarning: You have not specified a value for the `type` parameter. Defaulting to the 'tuples' format for chatbot messages, but this is deprecated and will be removed in a future version of Gradio. Please set type='messages' instead, which uses openai-style 'role' and 'content' keys. +2024-10-21 01:51:38 | ERROR | stderr | warnings.warn( +2024-10-21 01:51:38 | ERROR | stderr | +2024-10-21 01:51:38 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-21 01:51:38 | ERROR | stderr |  +2024-10-21 01:51:38 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-21 01:51:38 | ERROR | stderr | +2024-10-21 01:51:38 | INFO | httpx | HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK" +2024-10-21 01:51:38 | INFO | stdout | Cannot start Node server on any port in the range 7861-7861. +2024-10-21 01:51:38 | INFO | stdout | Please install Node 20 or higher and set the environment variable GRADIO_NODE_PATH to the path of your Node executable. +2024-10-21 01:51:38 | INFO | stdout | You can explicitly specify a port by setting the environment variable GRADIO_NODE_PORT. +2024-10-21 01:51:38 | INFO | stdout | * Running on local URL: http://0.0.0.0:7860, with SSR ⚡ +2024-10-21 01:51:38 | INFO | httpx | HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK" +2024-10-21 01:51:38 | INFO | httpx | HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK" +2024-10-21 01:51:38 | ERROR | stderr | /usr/local/lib/python3.10/site-packages/gradio/blocks.py:2595: UserWarning: Setting share=True is not supported on Hugging Face Spaces +2024-10-21 01:51:38 | ERROR | stderr | warnings.warn( +2024-10-21 01:51:38 | INFO | stdout | +2024-10-21 01:51:38 | INFO | stdout | To create a public link, set `share=True` in `launch()`. +2024-10-21 01:51:50 | INFO | stdout | conv mode to gemma +2024-10-21 01:51:50 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:51:50 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:51:50 | INFO | gradio_web_server | ==== request ==== +{'model': 'jadechoghari/Ferret-UI-Gemma2b', 'prompt': 'A chat between a human and an AI that understands visuals. In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. Increasing x moves right; y moves down. Bounding box: [x1, y1, x2, y2]. Image size: 1000x1000. Follow instructions.user\n\ndescribe this image in details\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['8b23f327b90b6211049acd36e3f99975']"} +2024-10-21 01:51:50 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:51:50 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=139926743686096&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NDY4MzcwfQ.Gw929SPxqMYGSBP897nuEjVF0jseYPhAEz1Y-DmaLBc "HTTP/1.1 200 OK" +2024-10-21 01:51:50 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=18 +2024-10-21 01:51:50 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=20 +2024-10-21 01:51:50 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[14, 15, 13, 10] +2024-10-21 01:51:51 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=963a6f92197f83506e17bc89e9eed7b10479d698dd11d5195a64f3d80fb999b4&pid=170045 "HTTP/1.1 200 OK" +2024-10-21 01:51:52 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 01:51:54 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 01:51:54 | ERROR | stderr | +2024-10-21 01:51:54 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00user\n\ndescribe what's in the image\nmodel\n", 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['8b23f327b90b6211049acd36e3f99975']"} +2024-10-21 01:52:49 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:52:49 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=139743490350032&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NDY4NDI5fQ.YfSg2L93_3ps3X0U8laMR6nBtlNqz2Tg5TGzWxqiR5Y "HTTP/1.1 200 OK" +2024-10-21 01:52:49 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=18 +2024-10-21 01:52:49 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=20 +2024-10-21 01:52:49 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[15, 10, 14, 13] +2024-10-21 01:52:50 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=1cd4e4e0edc771d7d6ec8b9c6cae2248487e70d5e19a074076e2a269bf57dcae&pid=170566 "HTTP/1.1 200 OK" +2024-10-21 01:52:51 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 01:52:53 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 01:52:53 | ERROR | stderr | +2024-10-21 01:52:53 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00user\n\ndescribe the image in details\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['8b23f327b90b6211049acd36e3f99975']"} +2024-10-21 01:53:59 | INFO | stdout | Input Image Size:(400, 433) +2024-10-21 01:53:59 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=139729682602960&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NDY4NDk5fQ.uJiGTTdYN3LxN4DmVcfZ1_-FHC8RgDZT4h8FvjGi_sQ "HTTP/1.1 200 OK" +2024-10-21 01:53:59 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=18 +2024-10-21 01:53:59 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=20 +2024-10-21 01:53:59 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[10, 15, 12, 14] +2024-10-21 01:54:00 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=8d8b7379cac569b30014b4cb23dfc7f48c288d5de95672319efb6d01b1d9f3dd&pid=171173 "HTTP/1.1 200 OK" +2024-10-21 01:54:01 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 01:54:02 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 01:54:02 | ERROR | stderr | +2024-10-21 01:54:02 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00user\n\nexplain what you see in details\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['f5fd9bd8b1445ded1d843253a97af861']"} +2024-10-21 05:32:22 | INFO | stdout | Input Image Size:(400, 668) +2024-10-21 05:32:22 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=140011682618320&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjE3NC45NS4xNC4xMDMiLCJ1c2VyIjpudWxsLCJ1dWlkIjpudWxsLCJleHAiOjE3Mjk0ODE2MDF9.p91aavRNfUhXhtR7_xDR77uWW9J_eXQ1QwzzxprUW6o "HTTP/1.1 200 OK" +2024-10-21 05:32:22 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=19 +2024-10-21 05:32:22 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=21 +2024-10-21 05:32:22 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[13, 10, 15, 16, 14] +2024-10-21 05:32:22 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=f829e9a779857a63f21056211fbd00a7e0862eb63292764ba63eef4c2a077c9e&pid=185515 "HTTP/1.1 200 OK" +2024-10-21 05:32:23 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 05:32:25 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 05:32:25 | ERROR | stderr | +2024-10-21 05:32:25 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00user\n\ndescribe what you see in details\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['f5fd9bd8b1445ded1d843253a97af861']"} +2024-10-21 05:38:53 | INFO | stdout | Input Image Size:(400, 668) +2024-10-21 05:38:54 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=140444052265936&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjE3NC45NS4xNC4xMDMiLCJ1c2VyIjpudWxsLCJ1dWlkIjpudWxsLCJleHAiOjE3Mjk0ODE5OTN9.DO6np5naKQ1opgWXq2boYpo1tnT03S0GqyfQXdOKzlE "HTTP/1.1 200 OK" +2024-10-21 05:38:54 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=18 +2024-10-21 05:38:54 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=20 +2024-10-21 05:38:54 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[15, 10, 14, 13] +2024-10-21 05:38:54 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=56e1b8cdad52721947b30e3765349a5e54c874886f781ea271756ba197927279&pid=186806 "HTTP/1.1 200 OK" +2024-10-21 05:38:55 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 05:38:56 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 05:38:56 | ERROR | stderr | +2024-10-21 05:38:56 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00user\n\ndescribe what you see in details\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['96dd1c245601ae0ca04ae1c44014cff7']"} +2024-10-21 05:53:39 | INFO | stdout | Input Image Size:(711, 400) +2024-10-21 05:53:40 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=140636289833936&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjE3NC45NS4xNC4xMDMiLCJ1c2VyIjpudWxsLCJ1dWlkIjpudWxsLCJleHAiOjE3Mjk0ODI4Nzl9.wCqodtwM7-0MHRoPHtSwhvf_0Iiwh3KpM2ZK9I804Rw "HTTP/1.1 200 OK" +2024-10-21 05:53:40 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=18 +2024-10-21 05:53:40 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=20 +2024-10-21 05:53:40 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[10, 13, 16, 14] +2024-10-21 05:53:40 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=5cbcde5d68c7e3714f9c161548cdbb3f80a55c14d22fbbd92f3ab3e017c798a3&pid=189326 "HTTP/1.1 200 OK" +2024-10-21 05:53:41 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 05:53:43 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 05:53:43 | ERROR | stderr | +2024-10-21 05:53:43 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00user\n\ndescribe what you see in details\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['a8d832a4d4163a69b808476963cc7c2a']"} +2024-10-21 05:57:11 | INFO | stdout | Input Image Size:(711, 400) +2024-10-21 05:57:11 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=140684771810256&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjE3NC45NS4xNC4xMDMiLCJ1c2VyIjpudWxsLCJ1dWlkIjpudWxsLCJleHAiOjE3Mjk0ODMwOTF9.kJBme1P0skhNBJ1Wc8892IB8QjufbWA5v28nDb_TipU "HTTP/1.1 200 OK" +2024-10-21 05:57:11 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=19 +2024-10-21 05:57:11 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=21 +2024-10-21 05:57:11 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[14, 15, 13, 16, 10] +2024-10-21 05:57:12 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=6ffcf6507ed7c3655ae17b6c4f53b8e83029298479520a2fb1d217b8bcf5561f&pid=190167 "HTTP/1.1 200 OK" +2024-10-21 05:57:13 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 05:57:14 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 05:57:14 | ERROR | stderr | +2024-10-21 05:57:14 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00, sep='', sep2='', version='gemma', skip_next=False) +2024-10-21 06:24:02 | ERROR | stderr | Traceback (most recent call last): +2024-10-21 06:24:02 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 407, in call_prediction +2024-10-21 06:24:02 | ERROR | stderr | output = await route_utils.call_process_api( +2024-10-21 06:24:02 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 226, in call_process_api +2024-10-21 06:24:02 | ERROR | stderr | output = await app.get_blocks().process_api( +2024-10-21 06:24:02 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1548, in process_api +2024-10-21 06:24:02 | ERROR | stderr | inputs = self.preprocess_data(fn_index, inputs, state) +2024-10-21 06:24:02 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1329, in preprocess_data +2024-10-21 06:24:02 | ERROR | stderr | processed_input.append(block.preprocess(inputs[i])) +2024-10-21 06:24:02 | ERROR | stderr | File "/home/user/app/app.py", line 558, in preprocess +2024-10-21 06:24:02 | ERROR | stderr | return super().preprocess(x) +2024-10-21 06:24:02 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/components/image.py", line 253, in preprocess +2024-10-21 06:24:02 | ERROR | stderr | assert isinstance(x, dict) +2024-10-21 06:24:02 | ERROR | stderr | AssertionError +2024-10-21 06:24:07 | ERROR | stderr | Traceback (most recent call last): +2024-10-21 06:24:07 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 407, in call_prediction +2024-10-21 06:24:07 | ERROR | stderr | output = await route_utils.call_process_api( +2024-10-21 06:24:07 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 226, in call_process_api +2024-10-21 06:24:07 | ERROR | stderr | output = await app.get_blocks().process_api( +2024-10-21 06:24:07 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1548, in process_api +2024-10-21 06:24:07 | ERROR | stderr | inputs = self.preprocess_data(fn_index, inputs, state) +2024-10-21 06:24:07 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1329, in preprocess_data +2024-10-21 06:24:07 | ERROR | stderr | processed_input.append(block.preprocess(inputs[i])) +2024-10-21 06:24:07 | ERROR | stderr | File "/home/user/app/app.py", line 558, in preprocess +2024-10-21 06:24:07 | ERROR | stderr | return super().preprocess(x) +2024-10-21 06:24:07 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/components/image.py", line 253, in preprocess +2024-10-21 06:24:07 | ERROR | stderr | assert isinstance(x, dict) +2024-10-21 06:24:07 | ERROR | stderr | AssertionError +2024-10-21 06:24:07 | ERROR | stderr | Traceback (most recent call last): +2024-10-21 06:24:07 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 407, in call_prediction +2024-10-21 06:24:07 | ERROR | stderr | output = await route_utils.call_process_api( +2024-10-21 06:24:07 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 226, in call_process_api +2024-10-21 06:24:07 | ERROR | stderr | output = await app.get_blocks().process_api( +2024-10-21 06:24:07 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1548, in process_api +2024-10-21 06:24:07 | ERROR | stderr | inputs = self.preprocess_data(fn_index, inputs, state) +2024-10-21 06:24:07 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1329, in preprocess_data +2024-10-21 06:24:07 | ERROR | stderr | processed_input.append(block.preprocess(inputs[i])) +2024-10-21 06:24:07 | ERROR | stderr | File "/home/user/app/app.py", line 558, in preprocess +2024-10-21 06:24:07 | ERROR | stderr | return super().preprocess(x) +2024-10-21 06:24:07 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/components/image.py", line 253, in preprocess +2024-10-21 06:24:07 | ERROR | stderr | assert isinstance(x, dict) +2024-10-21 06:24:07 | ERROR | stderr | AssertionError +2024-10-21 06:30:00 | INFO | httpx | HTTP Request: POST http://device-api.zero/startup-report "HTTP/1.1 200 OK" +2024-10-21 06:30:00 | INFO | gradio_web_server | args: Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=8, model_list_mode='once', share=False, moderate=False, embed=False, add_region_feature=False) +2024-10-21 06:30:00 | INFO | gradio_web_server | Models: ['jadechoghari/Ferret-UI-Gemma2b'] +2024-10-21 06:30:00 | INFO | gradio_web_server | Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=8, model_list_mode='once', share=False, moderate=False, embed=False, add_region_feature=False) +2024-10-21 06:30:00 | ERROR | stderr | /home/user/app/app.py:707: GradioDeprecationWarning: The `style` method is deprecated. Please set these arguments in the constructor instead. +2024-10-21 06:30:00 | ERROR | stderr | chatbot = gr.Chatbot(elem_id="chatbot", label="FERRET", visible=False).style(height=750) +2024-10-21 06:30:00 | ERROR | stderr | +2024-10-21 06:30:00 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-21 06:30:00 | ERROR | stderr |  +2024-10-21 06:30:00 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-21 06:30:00 | ERROR | stderr | +2024-10-21 06:30:00 | INFO | stdout | Running on local URL: http://0.0.0.0:7860 +2024-10-21 06:30:00 | ERROR | stderr | /usr/local/lib/python3.10/site-packages/gradio/blocks.py:2134: UserWarning: Setting share=True is not supported on Hugging Face Spaces +2024-10-21 06:30:00 | ERROR | stderr | warnings.warn( +2024-10-21 06:30:00 | INFO | stdout | +2024-10-21 06:30:00 | INFO | stdout | To create a public link, set `share=True` in `launch()`. +2024-10-21 06:30:00 | INFO | stdout | IMPORTANT: You are using gradio version 3.50.2, however version 4.44.1 is available, please upgrade. +2024-10-21 06:30:00 | INFO | stdout | -------- +2024-10-21 06:30:01 | INFO | stdout | state Conversation(system='A chat between a human and an AI that understands visuals. In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. Increasing x moves right; y moves down. Bounding box: [x1, y1, x2, y2]. Image size: 1000x1000. Follow instructions.', roles=('user', 'model'), messages=[], offset=0, sep_style=, sep='', sep2='', version='gemma', skip_next=False) +2024-10-21 06:30:23 | ERROR | stderr | Traceback (most recent call last): +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 407, in call_prediction +2024-10-21 06:30:23 | ERROR | stderr | output = await route_utils.call_process_api( +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 226, in call_process_api +2024-10-21 06:30:23 | ERROR | stderr | output = await app.get_blocks().process_api( +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1548, in process_api +2024-10-21 06:30:23 | ERROR | stderr | inputs = self.preprocess_data(fn_index, inputs, state) +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1329, in preprocess_data +2024-10-21 06:30:23 | ERROR | stderr | processed_input.append(block.preprocess(inputs[i])) +2024-10-21 06:30:23 | ERROR | stderr | File "/home/user/app/app.py", line 558, in preprocess +2024-10-21 06:30:23 | ERROR | stderr | return super().preprocess(x) +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/components/image.py", line 253, in preprocess +2024-10-21 06:30:23 | ERROR | stderr | assert isinstance(x, dict) +2024-10-21 06:30:23 | ERROR | stderr | AssertionError +2024-10-21 06:30:23 | ERROR | stderr | Traceback (most recent call last): +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 407, in call_prediction +2024-10-21 06:30:23 | ERROR | stderr | output = await route_utils.call_process_api( +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 226, in call_process_api +2024-10-21 06:30:23 | ERROR | stderr | output = await app.get_blocks().process_api( +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1550, in process_api +2024-10-21 06:30:23 | ERROR | stderr | result = await self.call_function( +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1199, in call_function +2024-10-21 06:30:23 | ERROR | stderr | prediction = await utils.async_iteration(iterator) +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 519, in async_iteration +2024-10-21 06:30:23 | ERROR | stderr | return await iterator.__anext__() +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 512, in __anext__ +2024-10-21 06:30:23 | ERROR | stderr | return await anyio.to_thread.run_sync( +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync +2024-10-21 06:30:23 | ERROR | stderr | return await get_async_backend().run_sync_in_worker_thread( +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2441, in run_sync_in_worker_thread +2024-10-21 06:30:23 | ERROR | stderr | return await future +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 943, in run +2024-10-21 06:30:23 | ERROR | stderr | result = context.run(func, *args) +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 495, in run_sync_iterator_async +2024-10-21 06:30:23 | ERROR | stderr | return next(iterator) +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 649, in gen_wrapper +2024-10-21 06:30:23 | ERROR | stderr | yield from f(*args, **kwargs) +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 295, in gradio_handler +2024-10-21 06:30:23 | ERROR | stderr | schedule_response = client.schedule(task_id=task_id, request=request, duration=duration_) +2024-10-21 06:30:23 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/spaces/zero/client.py", line 102, in schedule +2024-10-21 06:30:23 | ERROR | stderr | raise RuntimeError("ZeroGPU is only compatible with Gradio 4+") +2024-10-21 06:30:23 | ERROR | stderr | RuntimeError: ZeroGPU is only compatible with Gradio 4+ +2024-10-21 15:19:28 | INFO | stdout | state Conversation(system='A chat between a human and an AI that understands visuals. In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. Increasing x moves right; y moves down. Bounding box: [x1, y1, x2, y2]. Image size: 1000x1000. Follow instructions.', roles=('user', 'model'), messages=[], offset=0, sep_style=, sep='', sep2='', version='gemma', skip_next=False) +2024-10-21 15:20:26 | INFO | gradio_web_server | args: Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-21 15:20:26 | INFO | gradio_web_server | Models: ['jadechoghari/Ferret-UI-Gemma2b'] +2024-10-21 15:20:26 | INFO | gradio_web_server | Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-21 15:20:26 | ERROR | stderr | Traceback (most recent call last): +2024-10-21 15:20:26 | ERROR | stderr | File "/home/user/app/app.py", line 526, in +2024-10-21 15:20:26 | ERROR | stderr | demo = build_demo(args.embed, concurrency_count=args.concurrency_count) +2024-10-21 15:20:26 | ERROR | stderr | File "/home/user/app/app.py", line 378, in build_demo +2024-10-21 15:20:26 | ERROR | stderr | gr.Examples(examples=[ +2024-10-21 15:20:26 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/helpers.py", line 58, in create_examples +2024-10-21 15:20:26 | ERROR | stderr | examples_obj = Examples( +2024-10-21 15:20:26 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/helpers.py", line 209, in __init__ +2024-10-21 15:20:26 | ERROR | stderr | self.processed_examples = [ +2024-10-21 15:20:26 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/helpers.py", line 210, in +2024-10-21 15:20:26 | ERROR | stderr | [ +2024-10-21 15:20:26 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/helpers.py", line 211, in +2024-10-21 15:20:26 | ERROR | stderr | component.postprocess(sample) +2024-10-21 15:20:26 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio/components/image.py", line 301, in postprocess +2024-10-21 15:20:26 | ERROR | stderr | return client_utils.encode_url_or_file_to_base64(y) +2024-10-21 15:20:26 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio_client/utils.py", line 400, in encode_url_or_file_to_base64 +2024-10-21 15:20:26 | ERROR | stderr | return encode_file_to_base64(path) +2024-10-21 15:20:26 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/gradio_client/utils.py", line 373, in encode_file_to_base64 +2024-10-21 15:20:26 | ERROR | stderr | with open(f, "rb") as file: +2024-10-21 15:20:26 | ERROR | stderr | FileNotFoundError: [Errno 2] No such file or directory: '/home/user/app/examples/extreme_ironing.jpg' +2024-10-21 15:20:27 | INFO | stdout | IMPORTANT: You are using gradio version 3.50.2, however version 4.44.1 is available, please upgrade. +2024-10-21 15:20:27 | INFO | stdout | -------- +2024-10-21 15:21:27 | INFO | gradio_web_server | args: Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-21 15:21:27 | INFO | gradio_web_server | Models: ['jadechoghari/Ferret-UI-Gemma2b'] +2024-10-21 15:21:27 | INFO | gradio_web_server | Namespace(host='0.0.0.0', port=None, controller_url='http://localhost:21001', concurrency_count=16, model_list_mode='once', share=False, moderate=False, embed=False) +2024-10-21 15:21:27 | ERROR | stderr | /usr/local/lib/python3.10/site-packages/gradio/components/chatbot.py:222: UserWarning: You have not specified a value for the `type` parameter. Defaulting to the 'tuples' format for chatbot messages, but this is deprecated and will be removed in a future version of Gradio. Please set type='messages' instead, which uses openai-style 'role' and 'content' keys. +2024-10-21 15:21:27 | ERROR | stderr | warnings.warn( +2024-10-21 15:21:27 | ERROR | stderr | +2024-10-21 15:21:27 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-21 15:21:27 | ERROR | stderr |  +2024-10-21 15:21:27 | ERROR | stderr | ZeroGPU tensors packing: 0.00B [00:00, ?B/s] +2024-10-21 15:21:27 | ERROR | stderr | +2024-10-21 15:21:27 | INFO | httpx | HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK" +2024-10-21 15:21:27 | INFO | stdout | Cannot start Node server on any port in the range 7861-7861. +2024-10-21 15:21:27 | INFO | stdout | Please install Node 20 or higher and set the environment variable GRADIO_NODE_PATH to the path of your Node executable. +2024-10-21 15:21:27 | INFO | stdout | You can explicitly specify a port by setting the environment variable GRADIO_NODE_PORT. +2024-10-21 15:21:27 | INFO | stdout | * Running on local URL: http://0.0.0.0:7860, with SSR ⚡ +2024-10-21 15:21:27 | INFO | httpx | HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK" +2024-10-21 15:21:27 | INFO | httpx | HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK" +2024-10-21 15:21:27 | ERROR | stderr | /usr/local/lib/python3.10/site-packages/gradio/blocks.py:2595: UserWarning: Setting share=True is not supported on Hugging Face Spaces +2024-10-21 15:21:27 | ERROR | stderr | warnings.warn( +2024-10-21 15:21:27 | INFO | stdout | +2024-10-21 15:21:27 | INFO | stdout | To create a public link, set `share=True` in `launch()`. +2024-10-21 15:21:46 | INFO | stdout | conv mode to gemma +2024-10-21 15:21:46 | INFO | stdout | Input Image Size:(400, 586) +2024-10-21 15:21:46 | INFO | stdout | Input Image Size:(400, 586) +2024-10-21 15:21:46 | INFO | gradio_web_server | ==== request ==== +{'model': 'jadechoghari/Ferret-UI-Gemma2b', 'prompt': 'A chat between a human and an AI that understands visuals. In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. Increasing x moves right; y moves down. Bounding box: [x1, y1, x2, y2]. Image size: 1000x1000. Follow instructions.user\n\ndescribe what you see in details\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['9c4c9c437ec882a11cd6ed69ca2e5bd9']"} +2024-10-21 15:21:46 | INFO | stdout | Input Image Size:(400, 586) +2024-10-21 15:21:46 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=139775176089968&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjE3NC45NS4xNC4xMDMiLCJ1c2VyIjpudWxsLCJ1dWlkIjpudWxsLCJleHAiOjE3Mjk1MTY5NjV9.qLaq1aSTKyQFMb4jYz4gh6lcjEyoBb-c0kExK8OCQ_A "HTTP/1.1 200 OK" +2024-10-21 15:21:46 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=19 +2024-10-21 15:21:46 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=21 +2024-10-21 15:21:46 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[13, 16, 15, 14, 10] +2024-10-21 15:21:48 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=90594bf5adbb1f0fbad2418828d795c18aff5114b5a091cc6fe2990576355d0c&pid=276553 "HTTP/1.1 200 OK" +2024-10-21 15:21:51 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 15:21:53 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 15:21:53 | ERROR | stderr | +2024-10-21 15:21:53 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00user\n\ndescribe what yu see\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['a8d832a4d4163a69b808476963cc7c2a']"} +2024-10-21 15:25:04 | INFO | stdout | Input Image Size:(711, 400) +2024-10-21 15:25:04 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=139775176089968&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjE3NC45NS4xNC4xMDMiLCJ1c2VyIjpudWxsLCJ1dWlkIjpudWxsLCJleHAiOjE3Mjk1MTcxNjR9.2zZc9or3824jHnPazde4CnL-jpFez8IzA64nu76Fj18 "HTTP/1.1 200 OK" +2024-10-21 15:25:04 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=17 +2024-10-21 15:25:04 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=19 +2024-10-21 15:25:04 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[14, 13, 10] +2024-10-21 15:25:05 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=552cebcdaaeaf996a9ccf0f05254ae82ed1d550ecfdf2f53b2266fd34562562f&pid=277527 "HTTP/1.1 200 OK" +2024-10-21 15:25:06 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 15:25:09 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 15:25:09 | ERROR | stderr | +2024-10-21 15:25:09 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00user\n\nexplain what you see\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['9c4c9c437ec882a11cd6ed69ca2e5bd9']"} +2024-10-21 15:30:07 | INFO | stdout | Input Image Size:(400, 586) +2024-10-21 15:30:07 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=140591834374368&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjE3NC45NS4xNC4xMDMiLCJ1c2VyIjpudWxsLCJ1dWlkIjpudWxsLCJleHAiOjE3Mjk1MTc0Njd9.FO_xW1qpWy5go8eu0WetKo52DsHpADqDzjUkhlosPpY "HTTP/1.1 200 OK" +2024-10-21 15:30:07 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=20 +2024-10-21 15:30:07 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=22 +2024-10-21 15:30:07 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[16, 17, 12, 10, 15] +2024-10-21 15:30:08 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=648b429f91568bfe157028beedea7b464bb4a712abaa2d581c0972a2a6cc692f&pid=279039 "HTTP/1.1 200 OK" +2024-10-21 15:30:09 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 15:30:11 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 15:30:11 | ERROR | stderr | +2024-10-21 15:30:11 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00user\n\nexplain what's happening\nmodel\n", 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['f829af6c9ae32318da1e4c5a67d2978a']"} +2024-10-21 17:49:15 | INFO | stdout | Input Image Size:(400, 476) +2024-10-21 17:49:15 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=140591834374368&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NTI1ODE1fQ.en-6YG4Esy4uaUREqaQbsfwoyqqO-a3WBMu_SA0EQUE "HTTP/1.1 200 OK" +2024-10-21 17:49:15 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=19 +2024-10-21 17:49:15 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=21 +2024-10-21 17:49:15 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[12, 10, 16, 15, 14] +2024-10-21 17:49:16 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=a59f3af09d85a87e0044ddf7cd4278d20578a1c68e0f792588aec40df4acac2a&pid=289902 "HTTP/1.1 200 OK" +2024-10-21 17:49:19 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 17:49:22 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 17:49:22 | ERROR | stderr | +2024-10-21 17:49:22 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00user\n\ndescribe this image in details\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['209a525bc0390cad9c1e5ae87c12d79f']"} +2024-10-21 17:55:46 | INFO | stdout | Input Image Size:(400, 403) +2024-10-21 17:55:47 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=140591834374368&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NTI2MjA2fQ.YN2DYBaW_AUn8UpMenRW36SNGCEm_w2aRsVeLC2nBDY "HTTP/1.1 200 OK" +2024-10-21 17:55:47 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=18 +2024-10-21 17:55:47 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=20 +2024-10-21 17:55:47 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[16, 14, 10, 12] +2024-10-21 17:55:48 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=a7ee20da2ec36b200f351ec3391e6771f38fd843aa77b69ca836198160c9443f&pid=291152 "HTTP/1.1 200 OK" +2024-10-21 17:55:49 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 17:55:51 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 17:55:51 | ERROR | stderr | +2024-10-21 17:55:51 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00user\n\nexplaon what you see\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['f829af6c9ae32318da1e4c5a67d2978a']"} +2024-10-21 18:01:19 | INFO | stdout | Input Image Size:(400, 476) +2024-10-21 18:01:19 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=140314165141728&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NTI2NTM5fQ.x_oXSstHrzVPUMyDzPkwNGcF869Nz9tYNxIZncXaoCE "HTTP/1.1 200 OK" +2024-10-21 18:01:19 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=17 +2024-10-21 18:01:19 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=20 +2024-10-21 18:01:19 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[10, 19, 14, 13] +2024-10-21 18:01:19 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=6aad5e074610a6052fb447ebc0079dad9360486958bd9ad8f0adb5c5a3ef8b38&pid=292458 "HTTP/1.1 200 OK" +2024-10-21 18:01:24 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 18:01:26 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 18:01:26 | ERROR | stderr | +2024-10-21 18:01:26 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00user\n\nwhats in the image\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['36da526e3e0ad24decff5808117b2363']"} +2024-10-21 18:07:43 | INFO | stdout | Input Image Size:(362, 410) +2024-10-21 18:07:44 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=140314165141728&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NTI2OTIzfQ.U9crN9izZgU9SnmD8kiNIRDk3TRq37naVSMZoeI7s9M "HTTP/1.1 200 OK" +2024-10-21 18:07:44 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=21 +2024-10-21 18:07:44 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=23 +2024-10-21 18:07:44 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[18, 10, 13, 14, 16, 15, 17] +2024-10-21 18:07:44 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=a79d6c3e36a109df9a0f4cf64855ac18552d412274e7d8250a318c982ac50d55&pid=293629 "HTTP/1.1 200 OK" +2024-10-21 18:07:46 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 18:07:48 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 18:07:48 | ERROR | stderr | +2024-10-21 18:07:48 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00user\n\ndescribe what you see\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['bba68c82a3a4976b167abf9be5d2ade2']"} +2024-10-21 18:09:12 | INFO | stdout | Input Image Size:(58, 88) +2024-10-21 18:09:12 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=140709126037728&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NTI3MDEyfQ.iQWM9MG_RBZh1bOvosbxHR4X3EoDj0vtn8MY_ze6CKc "HTTP/1.1 200 OK" +2024-10-21 18:09:12 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=19 +2024-10-21 18:09:12 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=21 +2024-10-21 18:09:12 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[15, 13, 14, 10, 17] +2024-10-21 18:09:12 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=d1a4b976d7f8bbf9abc5c79094ecc79724e2cc38b8460a4ab3f5bc8fff546245&pid=294147 "HTTP/1.1 200 OK" +2024-10-21 18:09:14 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 18:09:16 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 18:09:16 | ERROR | stderr | +2024-10-21 18:09:16 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00user\n\ndescribe what you see\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['f829af6c9ae32318da1e4c5a67d2978a']"} +2024-10-21 18:10:23 | INFO | stdout | Input Image Size:(400, 476) +2024-10-21 18:10:23 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=140205599776992&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NTI3MDgzfQ.aE57FrJwtRazB0lzIzHCNQl10D769QDcOBfuD-sa2EU "HTTP/1.1 200 OK" +2024-10-21 18:10:23 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=20 +2024-10-21 18:10:23 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=22 +2024-10-21 18:10:23 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[15, 16, 10, 17, 13, 14] +2024-10-21 18:10:23 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=9c9f5876a2fe78e58a0a17f49f39fd7b7e7dfe5831c81134583c30b5c60fb094&pid=294631 "HTTP/1.1 200 OK" +2024-10-21 18:10:24 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 18:10:26 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 18:10:26 | ERROR | stderr | +2024-10-21 18:10:26 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00user\n\ndescribe waht you see\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['f829af6c9ae32318da1e4c5a67d2978a']"} +2024-10-21 18:11:05 | INFO | stdout | Input Image Size:(400, 476) +2024-10-21 18:11:05 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=139907506462944&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NTI3MTI1fQ.RpMaP6ucRsiHLMJlkl8BVqmIqkWZD5c84VdNBVEFFAM "HTTP/1.1 200 OK" +2024-10-21 18:11:05 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=20 +2024-10-21 18:11:05 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=22 +2024-10-21 18:11:05 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[15, 10, 18, 13, 16, 14] +2024-10-21 18:11:06 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=06dda6b23bde95507be6016a00cc2c541af8a87032c4164221c6a257b3eb8cd3&pid=295036 "HTTP/1.1 200 OK" +2024-10-21 18:11:07 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 18:11:09 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 18:11:09 | ERROR | stderr | +2024-10-21 18:11:09 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00user\n\ndescribe waht you see in details\nmodel\n', 'temperature': 0.2, 'top_p': 0.7, 'max_new_tokens': 512, 'stop': '', 'images': "List of 1 images: ['36da526e3e0ad24decff5808117b2363']"} +2024-10-21 18:14:24 | INFO | stdout | Input Image Size:(362, 410) +2024-10-21 18:14:25 | INFO | httpx | HTTP Request: POST http://device-api.zero/schedule?cgroupPath=%2Fkubepods.slice%2Fkubepods-burstable.slice%2Fkubepods-burstable-podd01b5ff5_c2cc_4948_b3ed_1e8ea56d357d.slice%2Fcri-containerd-90f67dcd1b09d742955a3a5af322b4ae02beaf359f175274f45abcca942ae839.scope&taskId=140677354168544&enableQueue=true&token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpcCI6IjEyOS45Ny4xMjQuMjE1IiwidXNlciI6bnVsbCwidXVpZCI6bnVsbCwiZXhwIjoxNzI5NTI3MzI0fQ.oqmCIuuj-5US_LzyMPwA8kcLJIKg-LT-DGW8vRDoHnI "HTTP/1.1 200 OK" +2024-10-21 18:14:25 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=19 +2024-10-21 18:14:25 | INFO | stdout | SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=21 +2024-10-21 18:14:25 | INFO | stdout | SPACES_ZERO_GPU_DEBUG fds=[12, 15, 14, 16, 10] +2024-10-21 18:14:26 | INFO | httpx | HTTP Request: POST http://device-api.zero/allow?allowToken=c065cfb8eef785a48a711364ac47f4a076bf7b18865f3bb6328cc03325c0abbb&pid=295814 "HTTP/1.1 200 OK" +2024-10-21 18:14:27 | INFO | stdout | SPACES_ZERO_GPU_DEBUG total_duration_in_callback=0 +2024-10-21 18:14:29 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). +2024-10-21 18:14:29 | ERROR | stderr | +2024-10-21 18:14:29 | ERROR | stderr | Loading checkpoint shards: 0%| | 0/2 [00:00