ok i can train and sample a model with a custom tokenizer

model.py

@@ -11,12 +11,13 @@ from torch import nn
 
 @dataclass
 class ModelArgs:
+    # default hyperparameters for the Llama 7B model
     dim: int = 4096
     n_layers: int = 32
     n_heads: int = 32
     n_kv_heads: Optional[int] = None
-    vocab_size: int = -1  # defined later by tokenizer
-    multiple_of: int = 256  # make SwiGLU hidden layer size multiple of large power of 2
+    vocab_size: int = 32000
+    multiple_of: int = 256  # MLP hidden layer size will be multiple of
     norm_eps: float = 1e-5
     max_seq_len: int = 2048
     dropout: float = 0.0