Unable to use web app

[nikhilno1]

I am deploying the model as per the instructions, but I am getting either '404 Not found' or 405 'Method not allowed'. What am I doing wrong?

(gpt) nikhil_subscribed@fastai-1:~/ru_transformers$ uvicorn rest:app --reload --host 0.0.0.0
INFO:     Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
INFO:     Started reloader process [6759]
INFO:     TensorFlow version 2.1.0 available.
INFO:     PyTorch version 1.4.0 available.
INFO:     Better speed can be achieved with apex installed from https://www.github.com/nvidia/apex .
2020-03-08 14:21:07.099055: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2020-03-08 14:21:07.105627: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2300000000 Hz
2020-03-08 14:21:07.106342: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x5623f942d910 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-03-08 14:21:07.106381: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
2020-03-08 14:21:07.106523: I tensorflow/core/common_runtime/process_util.cc:147] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.
INFO:     127.0.0.1:60018 - "GET /gpt2_poetry/ HTTP/1.1" 405 Method Not Allowed
INFO:     127.0.0.1:60020 - "GET / HTTP/1.1" 404 Not Found
INFO:     127.0.0.1:60030 - "GET /gpt2_poetry HTTP/1.1" 307 Temporary Redirect
INFO:     127.0.0.1:60030 - "GET /gpt2_poetry/ HTTP/1.1" 405 Method Not Allowed
INFO:     127.0.0.1:60040 - "GET /gpt/medium HTTP/1.1" 404 Not Found

[nikhilno1]

Hi, I am a little confused. I used YTTM tokenizer to create my vocab. It created a yt.model output file. But when I invoke the 'run_generation.py' script it throws error because it cannot find 'vocab.json' & 'merges.txt'. Shouldn't the tokenizer step be generating these files?

(gpt) ubuntu@train-instance:~/ru_transformers$ python run_generation.py     --model_type=gpt2     --model_name_or_path=./gpt2/medium/
2020-03-08 12:59:39.290516: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2020-03-08 12:59:39.298424: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2300000000 Hz
2020-03-08 12:59:39.299943: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x564fe6bc43b0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-03-08 12:59:39.299983: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
2020-03-08 12:59:39.300140: I tensorflow/core/common_runtime/process_util.cc:147] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.
03/08/2020 12:59:39 - INFO - transformers.tokenization_utils -   Model name './gpt2/medium/' not found in model shortcut name list (gpt2, gpt2-medium, gpt2-large, distilgpt2). Assuming './gpt2/medium/' is a path or url to a directory containing tokenizer files.
03/08/2020 12:59:39 - INFO - transformers.tokenization_utils -   Didn't find file ./gpt2/medium/vocab.json. We won't load it.
03/08/2020 12:59:39 - INFO - transformers.tokenization_utils -   Didn't find file ./gpt2/medium/merges.txt. We won't load it.
03/08/2020 12:59:39 - INFO - transformers.tokenization_utils -   Didn't find file ./gpt2/medium/added_tokens.json. We won't load it.
03/08/2020 12:59:39 - INFO - transformers.tokenization_utils -   Didn't find file ./gpt2/medium/special_tokens_map.json. We won't load it.
03/08/2020 12:59:39 - INFO - transformers.tokenization_utils -   Didn't find file ./gpt2/medium/tokenizer_config.json. We won't load it.
Traceback (most recent call last):
  File "run_generation.py", line 204, in <module>
    main()
  File "run_generation.py", line 166, in main
    tokenizer = tokenizer_class.from_pretrained(args.model_name_or_path)
  File "/home/ubuntu/.anaconda/envs/gpt/lib/python3.7/site-packages/transformers/tokenization_utils.py", line 282, in from_pretrained
    return cls._from_pretrained(*inputs, **kwargs)
  File "/home/ubuntu/.anaconda/envs/gpt/lib/python3.7/site-packages/transformers/tokenization_utils.py", line 346, in _from_pretrained
    list(cls.vocab_files_names.values())))
OSError: Model name './gpt2/medium/' was not found in tokenizers model name list (gpt2, gpt2-medium, gpt2-large, distilgpt2). We assumed './gpt2/medium/' was a path or url to a directory containing vocabulary files named ['vocab.json', 'merges.txt'] but couldn't find such vocabulary files at this path or url.

[nikhilno1]

For the Web app part, figured out that we need to make a request as below: curl -d '{"prompt":"This is "}' -H "Content-Type: application/json" -X POST http://0.0.0.0:8000/ Would be good to add it to the README.

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.