MetaIX

/

GPT4-X-Alpaca-30B-4bit

like 162

Hi so in both KoboldAI Occams fork and 4 bit capable ooba its both coming back with the same error. Its unclear what is causing this as the version and machine that I have not updated is still working fine but all of the machines I have tried to install and load have not worked at all. Can you please confirm what might be causing this issue? its not totally apparent to me what changed
Internal: src/sentencepiece_processor.cc

RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())]

From Ooba

Traceback (most recent call last):
File "/workspace/text-generation-webui/server.py", line 921, in
shared.model, shared.tokenizer = load_model(shared.model_name)
File "/workspace/text-generation-webui/modules/models.py", line 229, in load_model
tokenizer = LlamaTokenizer.from_pretrained(Path(f"{shared.args.model_dir}/{model_name}/"), clean_up_tokenization_spaces=True)
File "/workspace/miniconda3/envs/textgen/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1811, in from_pretrained
return cls._from_pretrained(
File "/workspace/miniconda3/envs/textgen/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1965, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
File "/workspace/miniconda3/envs/textgen/lib/python3.10/site-packages/transformers/models/llama/tokenization_llama.py", line 96, in init
self.sp_model.Load(vocab_file)
File "/workspace/miniconda3/envs/textgen/lib/python3.10/site-packages/sentencepiece/init.py", line 905, in Load
return self.LoadFromFile(model_file)
File "/workspace/miniconda3/envs/textgen/lib/python3.10/site-packages/sentencepiece/init.py", line 310, in LoadFromFile
return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg)
RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())]

From KAI

sentencepiece_processor.cc(923) LOG(ERROR) src/sentencepiece_processor.cc(290) [model_] Model is not initialized.
Returns default value 0
ERROR | main:g:609 - An error has been caught in function 'g', process 'MainProcess' (359), thread 'MainThread' (140485838542656):
Traceback (most recent call last):

File "/workspace/KoboldAI/runtime/envs/koboldai/lib/python3.8/site-packages/eventlet/green/thread.py", line 43, in __thread_body
func(*args, **kwargs)
│ │ └ {}
│ └ ()
└ <bound method Thread._bootstrap of <Thread(Thread-62, started daemon 140480538463168)>>
File "/workspace/KoboldAI/runtime/envs/koboldai/lib/python3.8/threading.py", line 890, in _bootstrap
self._bootstrap_inner()
│ └ <function start_new_thread..wrap_bootstrap_inner at 0x7fc42c476c10>
└ <Thread(Thread-62, started daemon 140480538463168)>
File "/workspace/KoboldAI/runtime/envs/koboldai/lib/python3.8/site-packages/eventlet/green/thread.py", line 64, in wrap_bootstrap_inner
bootstrap_inner()
└ <bound method Thread._bootstrap_inner of <Thread(Thread-62, started daemon 140480538463168)>>
File "/workspace/KoboldAI/runtime/envs/koboldai/lib/python3.8/threading.py", line 932, in _bootstrap_inner
self.run()
│ └ <function Thread.run at 0x7fc5669b9940>
└ <Thread(Thread-62, started daemon 140480538463168)>
File "/workspace/KoboldAI/runtime/envs/koboldai/lib/python3.8/threading.py", line 870, in run
self._target(*self._args, **self._kwargs)
│ │ │ │ │ └ {}
│ │ │ │ └ <Thread(Thread-62, started daemon 140480538463168)>
│ │ │ └ (<socketio.server.Server object at 0x7fc43000d250>, '4nVKA6iQiTr-FeLUAAAB', 'FHLMbFRf-y0wxsPJAAAA', ['load_model', {'model': ...
│ │ └ <Thread(Thread-62, started daemon 140480538463168)>
│ └ <bound method Server._handle_event_internal of <socketio.server.Server object at 0x7fc43000d250>>
└ <Thread(Thread-62, started daemon 140480538463168)>
File "/workspace/KoboldAI/runtime/envs/koboldai/lib/python3.8/site-packages/socketio/server.py", line 731, in _handle_event_internal
r = server._trigger_event(data[0], namespace, sid, *data[1:])
│ │ │ │ │ └ ['load_model', {'model': 'NeoCustom', 'path': '/workspace/KoboldAI/models/GPT4-X-Alpaca-30B-Int4', 'use_gpu': True, 'key': ''...
│ │ │ │ └ '4nVKA6iQiTr-FeLUAAAB'
│ │ │ └ '/'
│ │ └ ['load_model', {'model': 'NeoCustom', 'path': '/workspace/KoboldAI/models/GPT4-X-Alpaca-30B-Int4', 'use_gpu': True, 'key': ''...
│ └ <function Server._trigger_event at 0x7fc430e2f160>
└ <socketio.server.Server object at 0x7fc43000d250>
File "/workspace/KoboldAI/runtime/envs/koboldai/lib/python3.8/site-packages/socketio/server.py", line 756, in _trigger_event
return self.handlers[namespace]event
│ │ │ │ └ ('4nVKA6iQiTr-FeLUAAAB', {'model': 'NeoCustom', 'path': '/workspace/KoboldAI/models/GPT4-X-Alpaca-30B-Int4', 'use_gpu': True,...
│ │ │ └ 'load_model'
│ │ └ '/'
│ └ {'/': {'get_model_info': <function get_model_info at 0x7fc42cd30430>, 'OAI_Key_Update': <function get_oai_models at 0x7fc42cd...
└ <socketio.server.Server object at 0x7fc43000d250>
File "/workspace/KoboldAI/runtime/envs/koboldai/lib/python3.8/site-packages/flask_socketio/init.py", line 282, in _handler
return self._handle_event(handler, message, namespace, sid,
│ │ │ │ │ └ '4nVKA6iQiTr-FeLUAAAB'
│ │ │ │ └ '/'
│ │ │ └ 'load_model'
│ │ └ <function UI_2_load_model at 0x7fc42cceedc0>
│ └ <function SocketIO._handle_event at 0x7fc4309d1ee0>
└ <flask_socketio.SocketIO object at 0x7fc43000d2b0>
File "/workspace/KoboldAI/runtime/envs/koboldai/lib/python3.8/site-packages/flask_socketio/init.py", line 828, in _handle_event
ret = handler(*args)
│ └ ({'model': 'NeoCustom', 'path': '/workspace/KoboldAI/models/GPT4-X-Alpaca-30B-Int4', 'use_gpu': True, 'key': '', 'gpu_layers'...
└ <function UI_2_load_model at 0x7fc42cceedc0>

File "aiserver.py", line 609, in g
return f(*a, **k)
│ │ └ {}
│ └ ({'model': 'NeoCustom', 'path': '/workspace/KoboldAI/models/GPT4-X-Alpaca-30B-Int4', 'use_gpu': True, 'key': '', 'gpu_layers'...
└ <function UI_2_load_model at 0x7fc42cceeaf0>

File "aiserver.py", line 8960, in UI_2_load_model
load_model(use_gpu=data['use_gpu'], gpu_layers=data['gpu_layers'], disk_layers=data['disk_layers'], online_model=data['online_model'], url=koboldai_vars.colaburl, use_8_bit=data['use_8_bit'], use_4_bit=data['use_4_bit'])
│ │ │ │ │ │ │ └ {'model': 'NeoCustom', 'path': '/workspace/KoboldAI/models/GPT4-X-Alpaca-30B-Int4', 'use_gpu': True, 'key': '', 'gpu_layers':...
│ │ │ │ │ │ └ {'model': 'NeoCustom', 'path': '/workspace/KoboldAI/models/GPT4-X-Alpaca-30B-Int4', 'use_gpu': True, 'key': '', 'gpu_layers':...
│ │ │ │ │ └ <koboldai_settings.koboldai_vars object at 0x7fc42ff75610>
│ │ │ │ └ {'model': 'NeoCustom', 'path': '/workspace/KoboldAI/models/GPT4-X-Alpaca-30B-Int4', 'use_gpu': True, 'key': '', 'gpu_layers':...
│ │ │ └ {'model': 'NeoCustom', 'path': '/workspace/KoboldAI/models/GPT4-X-Alpaca-30B-Int4', 'use_gpu': True, 'key': '', 'gpu_layers':...
│ │ └ {'model': 'NeoCustom', 'path': '/workspace/KoboldAI/models/GPT4-X-Alpaca-30B-Int4', 'use_gpu': True, 'key': '', 'gpu_layers':...
│ └ {'model': 'NeoCustom', 'path': '/workspace/KoboldAI/models/GPT4-X-Alpaca-30B-Int4', 'use_gpu': True, 'key': '', 'gpu_layers':...
└ <function load_model at 0x7fc42cd30af0>

File "aiserver.py", line 3231, in load_model
tokenizer = LlamaTokenizer.from_pretrained(koboldai_vars.custmodpth)
│ │ └ <koboldai_settings.koboldai_vars object at 0x7fc42ff75610>
│ └ <classmethod object at 0x7fc4309d6430>
└ <class 'transformers.models.llama.tokenization_llama.LlamaTokenizer'>

File "aiserver.py", line 128, in new_pretrainedtokenizerbase_from_pretrained
tokenizer = old_pretrainedtokenizerbase_from_pretrained(cls, *args, **kwargs)
│ │ │ └ {}
│ │ └ ('/workspace/KoboldAI/models/GPT4-X-Alpaca-30B-Int4',)
│ └ <class 'transformers.models.llama.tokenization_llama.LlamaTokenizer'>
└ <function PreTrainedTokenizerBase.from_pretrained at 0x7fc431cb7040>

File "/workspace/KoboldAI/runtime/envs/koboldai/lib/python3.8/site-packages/transformers/tokenization_utils_base.py", line 1811, in from_pretrained
return cls._from_pretrained(
│ └ <classmethod object at 0x7fc431cb8040>
└ <class 'transformers.models.llama.tokenization_llama.LlamaTokenizer'>
File "/workspace/KoboldAI/runtime/envs/koboldai/lib/python3.8/site-packages/transformers/tokenization_utils_base.py", line 1965, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
│ │ └ {'add_bos_token': True, 'add_eos_token': False, 'bos_token': AddedToken("", rstrip=False, lstrip=False, single_word=False,...
│ └ ()
└ <class 'transformers.models.llama.tokenization_llama.LlamaTokenizer'>
File "/workspace/KoboldAI/runtime/envs/koboldai/lib/python3.8/site-packages/transformers/models/llama/tokenization_llama.py", line 96, in init
self.sp_model.Load(vocab_file)
│ │ │ └ '/workspace/KoboldAI/models/GPT4-X-Alpaca-30B-Int4/tokenizer.model'
│ │ └ <function SentencePieceProcessor.Load at 0x7fc4345cca60>
│ └ <sentencepiece.SentencePieceProcessor; proxy of <Swig Object of type 'sentencepiece::SentencePieceProcessor *' at 0x7fc42c243...
└ LlamaTokenizer(name_or_path='/workspace/KoboldAI/models/GPT4-X-Alpaca-30B-Int4', vocab_size=0, model_max_length=1000000000000...
File "/workspace/KoboldAI/runtime/envs/koboldai/lib/python3.8/site-packages/sentencepiece/__init__.py", line 905, in Load
return self.LoadFromFile(model_file)
│ │ └ '/workspace/KoboldAI/models/GPT4-X-Alpaca-30B-Int4/tokenizer.model'
│ └ <function SentencePieceProcessor.LoadFromFile at 0x7fc4345ca5e0>
└ <sentencepiece.SentencePieceProcessor; proxy of <Swig Object of type 'sentencepiece::SentencePieceProcessor *' at 0x7fc42c243...
File "/workspace/KoboldAI/runtime/envs/koboldai/lib/python3.8/site-packages/sentencepiece/__init__.py", line 310, in LoadFromFile
return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg)
│ │ │ └ '/workspace/KoboldAI/models/GPT4-X-Alpaca-30B-Int4/tokenizer.model'
│ │ └ <sentencepiece.SentencePieceProcessor; proxy of <Swig Object of type 'sentencepiece::SentencePieceProcessor *' at 0x7fc42c243...
│ └
└ <module 'sentencepiece._sentencepiece' from '/workspace/KoboldAI/runtime/envs/koboldai/lib/python3.8/site-packages/sentencepi...