---------------------------------------------------------------------------
ModuleNotFoundError                       Traceback (most recent call last)
Cell In[6], line 1
----> 1 from unsloth import FastLanguageModel
      2 model, tokenizer = FastLanguageModel.from_pretrained(
      3     model_name = "lora_model_loss3.0",
      4     max_seq_length= 2048, # Choose any for long context!
   (...)      7     # token = "hf_...", # use one if using gated models like meta-llama/Llama-2-7b-hf
      8 )

File ~/unslothfasz/lib/python3.12/site-packages/unsloth/__init__.py:243
    240     raise ImportError("Unsloth: Please install unsloth_zoo via `pip install unsloth_zoo`")
    241 pass
--> 243 from .models import *
    244 from .models import __version__
    245 from .save import *

File ~/unslothfasz/lib/python3.12/site-packages/unsloth/models/__init__.py:15
      1 # Copyright 2023-present Daniel Han-Chen & the Unsloth team. All rights reserved.
      2 #
      3 # Licensed under the Apache License, Version 2.0 (the "License");
   (...)     12 # See the License for the specific language governing permissions and
     13 # limitations under the License.
---> 15 from .llama     import FastLlamaModel
     16 from .loader    import FastLanguageModel, FastVisionModel, FastTextModel, FastModel
     17 from .mistral   import FastMistralModel

File ~/unslothfasz/lib/python3.12/site-packages/unsloth/models/llama.py:50
     48 if HAS_FLASH_ATTENTION:
     49     from flash_attn import flash_attn_func
---> 50 from .vision import FastBaseModel
     52 # Final patching code
     53 from transformers.models.llama.modeling_llama import (
     54     LlamaAttention,
     55     LlamaDecoderLayer,
     56     LlamaModel,
     57     LlamaForCausalLM,
     58 )

File ~/unslothfasz/lib/python3.12/site-packages/unsloth/models/vision.py:83
     76 _compile_config = CompileConfig(
     77     fullgraph = False,
     78     dynamic = None,
     79     mode = "reduce-overhead",
     80 )
     81 _compile_config.disable = True # Must set manually
---> 83 from unsloth_zoo.vllm_utils import (
     84     convert_lora_modules,
     85     return_lora_modules,
     86 )
     88 def unsloth_base_fast_generate(
     89     self,
     90     *args,
     91     **kwargs,
     92 ):
     93     if len(args) != 0:

File ~/unslothfasz/lib/python3.12/site-packages/unsloth_zoo/vllm_utils.py:95
     92     return vllm_check or unsloth_check
     93 pass
---> 95 import vllm.model_executor.layers.quantization.bitsandbytes
     97 if not hasattr(
     98     vllm.model_executor.layers.quantization.bitsandbytes,
     99     "apply_bnb_4bit"
    100 ):
    101     # Fix force using torch.bfloat16 all the time and make it dynamic
    102     def _apply_4bit_weight(
    103         self,
    104         layer: torch.nn.Module,
   (...)    107     ) -> torch.Tensor:
    108         # only load the bitsandbytes module when needed

ModuleNotFoundError: No module named 'vllm.model_executor'