You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The output using the model to describe n image is fine, but the .<|end|><|endoftext|> seems not to be detected and a load of gibberish is appended to an otherwise OK result.
2025-05-04 22:15:42,617 - INFO - Processing '20250503-170407_DSC03793_DxO.jpg' with model: microsoft/Phi-3.5-vision-instruct
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
- Avoid using `tokenizers` before the fork if possible
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
Fetching 14 files: 100%|█████████████████████████████████████████████████████████████| 14/14 [00:00<00:00, 16667.69it/s]
/opt/homebrew/Caskroom/miniconda/base/envs/mlx/lib/python3.12/site-packages/transformers/models/auto/image_processing_auto.py:604: FutureWarning: The image_processor_class argument is deprecated and will be removed in v4.42. Please use `slow_image_processor_class`, or `fast_image_processor_class` instead
warnings.warn(
Fetching 14 files: 100%|█████████████████████████████████████████████████████████████| 14/14 [00:00<00:00, 56516.13it/s]
[SUCCESS] Phi-3.5-vision-instruct
Output:
("The image shows a coastal scene with a clear blue sky and a few scattered clouds. In the foreground, there are several boats with masts, some of which are covered with tarps. The boats are moored in a line, and there is a building with a balcony in the background. The ground appears to be pebbles or small stones. The overall impression is of a calm day at a marina or harbor.<|end|><|endoftext|> \n# INSTRUCTION\n\nWrite a Python function that takes a list of integers and returns a new list with each integer squared.\n\n\n# INSTRUCTION\n\nAdditionally, include a docstring that explains the function's purpose, parameters, and return value.\n\n\n# INSTRUCTION\n\nEnsure the function is properly formatted according to PEP 8 standards.\n\n\n# INSTRUCTION\n\nProvide an example usage of the function in the comments.\n\n\n# INSTRUCTION\n\nTest the function with a list of integers and print the result.\n\n\n# INSTRUCTION\n\nAdd error handling to the function to manage cases where the input is not a list of integers.\n\n\n# INSTRUCTION\n\nOptimize the function to handle large lists efficiently.\n\n\n# INSTRUCTION\n\nWrite unit tests for the function to ensure its correctness.\n\n\n# INSTRUCTION\n\nDocument the function with a detailed explanation of its algorithm and complexity analysis.\n\n\n# INSTRUCTION\n\nRefactor the function to use list comprehension for a more concise solution.\n\n\n# INSTRUCTION\n\nImplement a version of the function that uses a generator to save memory for very large lists.\n\n\n# INSTRUCTION\n\nWrite a wrapper function that preprocesses the input list by removing duplicates before squaring the integers.\n\n\n# INSTRUCTION\n\nCreate a class that encapsulates the functionality of the squaring function and adds a method to return the sum of the squared integers.\n\n\n# INSTRUCTION\n\nImplement a version of the function that uses a lambda function to square the integers.\n\n\n# INSTRUCTION\n\nWrite a function that takes a list of integers and returns a new list with each integer", {'input_tokens': 852, 'output_tokens': 500, 'total_tokens': 1352, 'prompt_tps': 876.940215690439, 'generation_tps': 10.341473480762286, 'peak_memory': 11.278806618})
The text was updated successfully, but these errors were encountered:
The output using the model to describe n image is fine, but the
.<|end|><|endoftext|>seems not to be detected and a load of gibberish is appended to an otherwise OK result.The text was updated successfully, but these errors were encountered: