SillyTavern / SillyTavern-Extras

Extensions API for SillyTavern.
GNU Affero General Public License v3.0
563 stars 133 forks source link

Issue when loading alternate Summarization models #160

Open wereretot opened 1 year ago

wereretot commented 1 year ago

python3 server.py --classification-model joeddav/distilbert-base-uncased-go-emotions-student --enable-modules summarize,chromadb,classify,rvc,coqui-tts, --coqui-gpu --summarization-model=tuner007/pegasus_summarizer
Using torch device: cpu Initializing a text summarization model... Downloading (…)okenizer_config.json: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 1.61k/1.61k [00:00<00:00, 14.5MB/s] Downloading spiece.model: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1.91M/1.91M [00:00<00:00, 19.3MB/s] Downloading (…)cial_tokens_map.json: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 1.34k/1.34k [00:00<00:00, 13.1MB/s] Traceback (most recent call last): File "/home/rexommendation/Programs/SillyTavern-Extras/server.py", line 219, in summarization_tokenizer = AutoTokenizer.from_pretrained(summarization_model) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/rexommendation/Programs/SillyTavern-Extras/venv/lib/python3.11/site-packages/transformers/models/auto/tokenization_auto.py", line 702, in from_pretrained return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, *kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/rexommendation/Programs/SillyTavern-Extras/venv/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 1811, in from_pretrained return cls._from_pretrained( ^^^^^^^^^^^^^^^^^^^^^ File "/home/rexommendation/Programs/SillyTavern-Extras/venv/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 1965, in _from_pretrained tokenizer = cls(init_inputs, **init_kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/rexommendation/Programs/SillyTavern-Extras/venv/lib/python3.11/site-packages/transformers/models/pegasus/tokenization_pegasus_fast.py", line 142, in init super().init( File "/home/rexommendation/Programs/SillyTavern-Extras/venv/lib/python3.11/site-packages/transformers/tokenization_utils_fast.py", line 114, in init fast_tokenizer = convert_slow_tokenizer(slow_tokenizer) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/rexommendation/Programs/SillyTavern-Extras/venv/lib/python3.11/site-packages/transformers/convert_slow_tokenizer.py", line 1288, in convert_slow_tokenizer return converter_class(transformer_tokenizer).converted() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/rexommendation/Programs/SillyTavern-Extras/venv/lib/python3.11/site-packages/transformers/convert_slow_tokenizer.py", line 445, in init from .utils import sentencepiece_model_pb2 as model_pb2 File "/home/rexommendation/Programs/SillyTavern-Extras/venv/lib/python3.11/site-packages/transformers/utils/sentencepiece_model_pb2.py", line 91, in _descriptor.EnumValueDescriptor( File "/home/rexommendation/Programs/SillyTavern-Extras/venv/lib/python3.11/site-packages/google/protobuf/descriptor.py", line 796, in new _message.Message._CheckCalledFromGeneratedFile() TypeError: Descriptors cannot not be created directly. If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0. If you cannot immediately regenerate your protos, some other possible workarounds are:

  1. Downgrade the protobuf package to 3.20.x or lower.
  2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).

More information: https://developers.google.com/protocol-buffers/docs/news/2022-05-06#python-updates

Cohee1207 commented 1 year ago

Try the solution proposed by the error message: set the environment variable PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python