===================================BUG REPORT===================================
Welcome to bitsandbytes. For bug reports, please run

python -m bitsandbytes

 and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues
================================================================================
bin B:\python\lib\site-packages\bitsandbytes\libbitsandbytes_cuda118.dll
CUDA SETUP: CUDA runtime path found: B:\python\bin\cudart64_110.dll
CUDA SETUP: Highest compute capability among GPUs detected: 8.6
CUDA SETUP: Detected CUDA version 118
CUDA SETUP: Loading binary B:\python\lib\site-packages\bitsandbytes\libbitsandbytes_cuda118.dll...
ERROR      | __main__:g:723 - An error has been caught in function 'g', process 'MainProcess' (15240), thread 'MainThread' (4088):
Traceback (most recent call last):

  File "C:\KoboldAI\modeling\inference_models\gptq_hf_torch\class.py", line 383, in _get_model
    model = AutoGPTQForCausalLM.from_quantized(location, model_basename=Path(gptq_file).stem, use_safetensors=gptq_file.endswith(".safetensors"), device_map=device_map)
            │                   │              │                        │    │                                │         │                                    └ {'transformer.h.0': 0, 'transformer.h.1': 0, 'transformer.h.2': 0, 'transformer.h.3': 0, 'transformer.h.4': 0, 'transformer.h...
            │                   │              │                        │    │                                │         └ <method 'endswith' of 'str' objects>
            │                   │              │                        │    │                                └ 'C:\\KoboldAI\\models\\pygmalion-6b-gptq-4bit\\4bit-128g.pt'
            │                   │              │                        │    └ 'C:\\KoboldAI\\models\\pygmalion-6b-gptq-4bit\\4bit-128g.pt'
            │                   │              │                        └ <class 'pathlib.Path'>
            │                   │              └ 'C:\\KoboldAI\\models\\pygmalion-6b-gptq-4bit'
            │                   └ <classmethod object at 0x000001E5C48CEAF0>
            └ <class 'auto_gptq.modeling.auto.AutoGPTQForCausalLM'>

  File "B:\python\lib\site-packages\auto_gptq\modeling\auto.py", line 108, in from_quantized
    return quant_func(
           └ <bound method BaseGPTQForCausalLM.from_quantized of <class 'auto_gptq.modeling.gptj.GPTJGPTQForCausalLM'>>

  File "B:\python\lib\site-packages\auto_gptq\modeling\_base.py", line 757, in from_quantized
    quantize_config = BaseQuantizeConfig.from_pretrained(model_name_or_path, **cached_file_kwargs, **kwargs)
                      │                  │               │                     │                     └ {}
                      │                  │               │                     └ {'cache_dir': None, 'force_download': False, 'proxies': None, 'resume_download': False, 'local_files_only': False, 'use_auth_...
                      │                  │               └ 'C:\\KoboldAI\\models\\pygmalion-6b-gptq-4bit'
                      │                  └ <classmethod object at 0x000001E5C13B7F70>
                      └ <class 'auto_gptq.modeling._base.BaseQuantizeConfig'>

  File "B:\python\lib\site-packages\auto_gptq\modeling\_base.py", line 93, in from_pretrained
    with open(resolved_config_file, "r", encoding="utf-8") as f:
              └ 'C:\\KoboldAI\\models\\pygmalion-6b-gptq-4bit\\quantize_config.json'

FileNotFoundError: [Errno 2] No such file or directory: 'C:\\KoboldAI\\models\\pygmalion-6b-gptq-4bit\\quantize_config.json'


During handling of the above exception, another exception occurred:


Traceback (most recent call last):

  File "B:\python\lib\site-packages\eventlet\green\thread.py", line 43, in __thread_body
    func(*args, **kwargs)
    │     │       └ {}
    │     └ ()
    └ <bound method Thread._bootstrap of <Thread(Thread-28, started daemon 2086052263296)>>

  File "B:\python\lib\threading.py", line 890, in _bootstrap
    self._bootstrap_inner()
    │    └ <function start_new_thread.<locals>.wrap_bootstrap_inner at 0x000001E5B2897A60>
    └ <Thread(Thread-28, started daemon 2086052263296)>

  File "B:\python\lib\site-packages\eventlet\green\thread.py", line 64, in wrap_bootstrap_inner
    bootstrap_inner()
    └ <bound method Thread._bootstrap_inner of <Thread(Thread-28, started daemon 2086052263296)>>

  File "B:\python\lib\threading.py", line 932, in _bootstrap_inner
    self.run()
    │    └ <function Thread.run at 0x000001E5AA5B43A0>
    └ <Thread(Thread-28, started daemon 2086052263296)>

  File "B:\python\lib\threading.py", line 870, in run
    self._target(*self._args, **self._kwargs)
    │    │        │    │        │    └ {}
    │    │        │    │        └ <Thread(Thread-28, started daemon 2086052263296)>
    │    │        │    └ (<socketio.server.Server object at 0x000001E5AA9DC130>, 'SNJSBVSHvenOt6SKAAAB', 'bwGwIubSwmRC_rKxAAAA', ['load_model', {'0_La...
    │    │        └ <Thread(Thread-28, started daemon 2086052263296)>
    │    └ <bound method Server._handle_event_internal of <socketio.server.Server object at 0x000001E5AA9DC130>>
    └ <Thread(Thread-28, started daemon 2086052263296)>

  File "B:\python\lib\site-packages\socketio\server.py", line 731, in _handle_event_internal
    r = server._trigger_event(data[0], namespace, sid, *data[1:])
        │      │              │        │          │     └ ['load_model', {'0_Layers': 28, 'CPU_Layers': 0, 'Disk_Layers': 0, 'implementation': 'occam', 'class': 'model', 'label': 'pyg...
        │      │              │        │          └ 'SNJSBVSHvenOt6SKAAAB'
        │      │              │        └ '/'
        │      │              └ ['load_model', {'0_Layers': 28, 'CPU_Layers': 0, 'Disk_Layers': 0, 'implementation': 'occam', 'class': 'model', 'label': 'pyg...
        │      └ <function Server._trigger_event at 0x000001E5AA0CDC10>
        └ <socketio.server.Server object at 0x000001E5AA9DC130>

  File "B:\python\lib\site-packages\socketio\server.py", line 756, in _trigger_event
    return self.handlers[namespace][event](*args)
           │    │        │          │       └ ('SNJSBVSHvenOt6SKAAAB', {'0_Layers': 28, 'CPU_Layers': 0, 'Disk_Layers': 0, 'implementation': 'occam', 'class': 'model', 'la...
           │    │        │          └ 'load_model'
           │    │        └ '/'
           │    └ {'/': {'connect': <function do_connect at 0x000001E5B228E820>, 'message': <function get_message at 0x000001E5B228E9D0>, 'show...
           └ <socketio.server.Server object at 0x000001E5AA9DC130>

  File "B:\python\lib\site-packages\flask_socketio\__init__.py", line 282, in _handler
    return self._handle_event(handler, message, namespace, sid,
           │    │             │        │        │          └ 'SNJSBVSHvenOt6SKAAAB'
           │    │             │        │        └ '/'
           │    │             │        └ 'load_model'
           │    │             └ <function UI_2_load_model at 0x000001E5B22B28B0>
           │    └ <function SocketIO._handle_event at 0x000001E5AA581820>
           └ <flask_socketio.SocketIO object at 0x000001E5AA9DC4C0>

  File "B:\python\lib\site-packages\flask_socketio\__init__.py", line 828, in _handle_event
    ret = handler(*args)
          │        └ ({'0_Layers': 28, 'CPU_Layers': 0, 'Disk_Layers': 0, 'implementation': 'occam', 'class': 'model', 'label': 'pygmalion-6b-gptq...
          └ <function UI_2_load_model at 0x000001E5B22B28B0>

> File "aiserver.py", line 723, in g
    return f(*a, **k)
           │  │    └ {}
           │  └ ({'0_Layers': 28, 'CPU_Layers': 0, 'Disk_Layers': 0, 'implementation': 'occam', 'class': 'model', 'label': 'pygmalion-6b-gptq...
           └ <function UI_2_load_model at 0x000001E5B22B25E0>

  File "aiserver.py", line 6326, in UI_2_load_model
    load_model(data['plugin'])
    │          └ {'0_Layers': 28, 'CPU_Layers': 0, 'Disk_Layers': 0, 'implementation': 'occam', 'class': 'model', 'label': 'pygmalion-6b-gptq-...
    └ <function load_model at 0x000001E5B228B670>

  File "aiserver.py", line 1753, in load_model
    model.load(initial_load=initial_load, save_model=not (args.colab or args.cacheonly) or args.savemodel)
    │     │                 │                             │    │        │    │             │    └ False
    │     │                 │                             │    │        │    │             └ Namespace(apikey=None, aria2_port=None, cacheonly=False, colab=False, configname=None, cpu=False, customsettings=None, f=None...
    │     │                 │                             │    │        │    └ False
    │     │                 │                             │    │        └ Namespace(apikey=None, aria2_port=None, cacheonly=False, colab=False, configname=None, cpu=False, customsettings=None, f=None...
    │     │                 │                             │    └ False
    │     │                 │                             └ Namespace(apikey=None, aria2_port=None, cacheonly=False, colab=False, configname=None, cpu=False, customsettings=None, f=None...
    │     │                 └ False
    │     └ <function InferenceModel.load at 0x000001E5AA587670>
    └ <modeling.inference_models.gptq_hf_torch.class.model_backend object at 0x000001E5A6712A90>

  File "C:\KoboldAI\modeling\inference_model.py", line 211, in load
    self._load(save_model=save_model, initial_load=initial_load)
    │    │                │                        └ False
    │    │                └ True
    │    └ <function model_backend._load at 0x000001E5A672E3A0>
    └ <modeling.inference_models.gptq_hf_torch.class.model_backend object at 0x000001E5A6712A90>

  File "C:\KoboldAI\modeling\inference_models\gptq_hf_torch\class.py", line 233, in _load
    self.model = self._get_model(self.get_local_model_path())
    │    │       │    │          │    └ <function HFInferenceModel.get_local_model_path at 0x000001E5A67169D0>
    │    │       │    │          └ <modeling.inference_models.gptq_hf_torch.class.model_backend object at 0x000001E5A6712A90>
    │    │       │    └ <function model_backend._get_model at 0x000001E5A672E550>
    │    │       └ <modeling.inference_models.gptq_hf_torch.class.model_backend object at 0x000001E5A6712A90>
    │    └ None
    └ <modeling.inference_models.gptq_hf_torch.class.model_backend object at 0x000001E5A6712A90>

  File "C:\KoboldAI\modeling\inference_models\gptq_hf_torch\class.py", line 385, in _get_model
    model = AutoGPTQForCausalLM.from_quantized(location, model_basename=Path(gptq_file).stem, use_safetensors=gptq_file.endswith(".safetensors"), device_map=device_map, disable_exllama=True)
            │                   │              │                        │    │                                │         │                                    └ {'transformer.h.0': 0, 'transformer.h.1': 0, 'transformer.h.2': 0, 'transformer.h.3': 0, 'transformer.h.4': 0, 'transformer.h...
            │                   │              │                        │    │                                │         └ <method 'endswith' of 'str' objects>
            │                   │              │                        │    │                                └ 'C:\\KoboldAI\\models\\pygmalion-6b-gptq-4bit\\4bit-128g.pt'
            │                   │              │                        │    └ 'C:\\KoboldAI\\models\\pygmalion-6b-gptq-4bit\\4bit-128g.pt'
            │                   │              │                        └ <class 'pathlib.Path'>
            │                   │              └ 'C:\\KoboldAI\\models\\pygmalion-6b-gptq-4bit'
            │                   └ <classmethod object at 0x000001E5C48CEAF0>
            └ <class 'auto_gptq.modeling.auto.AutoGPTQForCausalLM'>

  File "B:\python\lib\site-packages\auto_gptq\modeling\auto.py", line 108, in from_quantized
    return quant_func(
           └ <bound method BaseGPTQForCausalLM.from_quantized of <class 'auto_gptq.modeling.gptj.GPTJGPTQForCausalLM'>>

  File "B:\python\lib\site-packages\auto_gptq\modeling\_base.py", line 757, in from_quantized
    quantize_config = BaseQuantizeConfig.from_pretrained(model_name_or_path, **cached_file_kwargs, **kwargs)
                      │                  │               │                     │                     └ {}
                      │                  │               │                     └ {'cache_dir': None, 'force_download': False, 'proxies': None, 'resume_download': False, 'local_files_only': False, 'use_auth_...
                      │                  │               └ 'C:\\KoboldAI\\models\\pygmalion-6b-gptq-4bit'
                      │                  └ <classmethod object at 0x000001E5C13B7F70>
                      └ <class 'auto_gptq.modeling._base.BaseQuantizeConfig'>

  File "B:\python\lib\site-packages\auto_gptq\modeling\_base.py", line 93, in from_pretrained
    with open(resolved_config_file, "r", encoding="utf-8") as f:
              └ 'C:\\KoboldAI\\models\\pygmalion-6b-gptq-4bit\\quantize_config.json'

FileNotFoundError: [Errno 2] No such file or directory: 'C:\\KoboldAI\\models\\pygmalion-6b-gptq-4bit\\quantize_config.json'
Connection Attempt: 127.0.0.1
INFO       | __main__:do_connect:2571 - Client connected! UI_2
Connection Attempt: 127.0.0.1
INFO       | __main__:do_connect:2571 - Client connected! UI_2