model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "unsloth/llama-3-8b-bnb-4bit",
    max_seq_length = max_seq_length,
    dtype = None,
    load_in_4bit = True,
)

==((====))==  Unsloth: Fast Llama patching release 2024.5
   \\   /|    GPU: NVIDIA GeForce RTX 4090. Max memory: 23.988 GB. Platform = Linux.
O^O/ \_/ \    Pytorch: 2.1.0+cu121. CUDA = 8.9. CUDA Toolkit = 12.1.
\        /    Bfloat16 = TRUE. Xformers = 0.0.22.post7. FA = False.
 "-____-"     Free Apache license: http://github.com/unslothai/unsloth

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[7], line 2
      1 # 2. Load Llama3 model
----> 2 model, tokenizer = FastLanguageModel.from_pretrained(
      3     model_name = "unsloth/llama-3-8b-bnb-4bit",
      4     max_seq_length = max_seq_length,
      5     dtype = None,
      6     load_in_4bit = True,
      7 )

File ~/miniconda/envs/llama3/lib/python3.9/site-packages/unsloth/models/loader.py:142, in FastLanguageModel.from_pretrained(model_name, max_seq_length, dtype, load_in_4bit, token, device_map, rope_scaling, fix_tokenizer, trust_remote_code, use_gradient_checkpointing, resize_model_vocab, *args, **kwargs)
    139     tokenizer_name = None
    140 pass
--> 142 model, tokenizer = dispatch_model.from_pretrained(
    143     model_name     = model_name,
    144     max_seq_length = max_seq_length,
    145     dtype          = dtype,
    146     load_in_4bit   = load_in_4bit,
    147     token          = token,
    148     device_map     = device_map,
    149     rope_scaling   = rope_scaling,
    150     fix_tokenizer  = fix_tokenizer,
    151     model_patcher  = dispatch_model,
    152     tokenizer_name = tokenizer_name,
...
     96         "You have a version of `bitsandbytes` that is not compatible with 4bit inference and training"
     97         " make sure you have the latest version of `bitsandbytes` installed"
     98     )