TypeError: not a string

[Farquaad56]

Hi, i have this issue when i load llama-7B on my RTX2080Ti

`(textgen) X:\LLama chat\text-generation-webui>python server.py --model llama-7b --load-in-8bit Loading llama-7b...

===================================BUG REPORT=================================== Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues

Loading checkpoint shards: 100%|███████████████████████████████████████████████████████| 33/33 [00:15<00:00, 2.13it/s] Traceback (most recent call last): File "X:\LLama chat\text-generation-webui\server.py", line 194, in shared.model, shared.tokenizer = load_model(shared.model_name) File "X:\LLama chat\text-generation-webui\modules\models.py", line 155, in load_model tokenizer = AutoTokenizer.from_pretrained(Path(f"models/{shared.model_name}/")) File "C:\Users\xx\anaconda3\envs\textgen\lib\site-packages\transformers\models\auto\tokenization_auto.py", line 679, in from_pretrained return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs) File "C:\Users\xx\anaconda3\envs\textgen\lib\site-packages\transformers\tokenization_utils_base.py", line 1804, in from_pretrained return cls.from_pretrained( File "C:\Users\xx\anaconda3\envs\textgen\lib\site-packages\transformers\tokenization_utils_base.py", line 1958, in from_pretrained tokenizer = cls(*init_inputs, **init_kwargs) File "C:\Users\xx\anaconda3\envs\textgen\lib\site-packages\transformers\models\llama\tokenization_llama.py", line 70, in init self.sp_model.Load(vocab_file) File "C:\Users\xx\anaconda3\envs\textgen\lib\site-packages\sentencepiece_init.py", line 905, in Load return self.LoadFromFile(model_file) File "C:\Users\xx\anaconda3\envs\textgen\lib\site-packages\sentencepiece_init.py", line 310, in LoadFromFile return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg) TypeError: not a string

(textgen) X:\LLama chat\text-generation-webui>`

[oobabooga]

Can you try reconverting the model following the instructions here?

https://github.com/oobabooga/text-generation-webui/wiki/LLaMA-model

[Farquaad56]

I restarted the conversion of the model with the last version script.uninstalled and reinstalled "transformer" with the "custom llama" version and I still have the same error message.

[BetaDoggo]

Did you move the tokenizer files into the model folder after converting? I made that mistake originally and had the same error.

[Farquaad56]

yes i have this files in "text-generation-webui\models\llama-7b" folder

• config.json
• generation_config.json
• pytorch_model.bin.index.json
• special_tokens_map.json
• tokenizer_config.json
• pytorch_model-00001-of-00033 to pytorch_model-00033-of-00033.bin

[BetaDoggo]

I believe you also need tokenizer.model. It might be in the folder of the original unconverted model rather than the one created by the conversion script.

[Farquaad56]

hi thanks, that was it i was missing this file ( tokenizer.model ), now i can launch the gui. i have a new error ( RuntimeError: CUDA error: an illegal memory access was encountered ) but my issue is solved. Thanks for answer