anon8231489123

/

gpt4-x-alpaca-13b-native-4bit-128g

like 734

I've installed Ooga Booga and I'm trying to run the model from the cuda weights but encounter the following error when starting the web ui

Traceback (most recent call last):
File "C:\Users\mm049\Desktop\ooga booga\text-generation-webui\server.py", line 302, in
shared.model, shared.tokenizer = load_model(shared.model_name)
File "C:\Users\mm049\Desktop\ooga booga\text-generation-webui\modules\models.py", line 181, in load_model
tokenizer = LlamaTokenizer.from_pretrained(Path(f"{shared.args.model_dir}/{shared.model_name}/"), clean_up_tokenization_spaces=True)
File "C:\Users\mm049\Desktop\ooga booga\installer_files\env\lib\site-packages\transformers\tokenization_utils_base.py", line 1811, in from_pretrained
return cls.from_pretrained(
File "C:\Users\mm049\Desktop\ooga booga\installer_files\env\lib\site-packages\transformers\tokenization_utils_base.py", line 1965, in from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
File "C:\Users\mm049\Desktop\ooga booga\installer_files\env\lib\site-packages\transformers\models\llama\tokenization_llama.py", line 96, in init
self.sp_model.Load(vocab_file)
File "C:\Users\mm049\Desktop\ooga booga\installer_files\env\lib\site-packages\sentencepiece_init.py", line 905, in Load
return self.LoadFromFile(model_file)
File "C:\Users\mm049\Desktop\ooga booga\installer_files\env\lib\site-packages\sentencepiece_init.py", line 310, in LoadFromFile
return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg)
RuntimeError: Internal: D:\a\sentencepiece\sentencepiece\src\sentencepiece_processor.cc(1102) [model_proto->ParseFromArray(serialized.data(), serialized.size())]

Does anyone have any insight on what might be causing this. I have confirmed that the checksum of my model weights matches the repository.