Upload trained model and tokenizer

configuration_minimalllm.py

@@ -1,4 +1,6 @@
 
+from transformers import PretrainedConfig
+
 class MinimalLLMConfig(PretrainedConfig):
     model_type = "minimal_llm"
 

modeling_minimalllm.py

@@ -44,7 +44,7 @@ class Rotary(nn.Module):
 
     def forward(self, x_BTHD: torch.Tensor):
         assert self.cos.size(0) >= x_BTHD.size(-3)
-        cos, sin = self.cos[None, :x_BTHD.size(-3), None, :], self.sin[None, :x_BTHD.size(-3), None, :]
+        cos, sin = self.cos[None, :x_BTHD.size(-3), None, :], self.sin[None, :x_BTHD.size(-3), None, :] 
         x1, x2 = x_BTHD.to(dtype=torch.float32).chunk(2, dim=-1)
         y1 = x1 * cos + x2 * sin
         y2 = x1 * (-sin) + x2 * cos
@@ -146,6 +146,11 @@ class TransformerBlock(nn.Module):
         return x
 
 
+from transformers import PreTrainedModel, GenerationMixin
+from transformers.modeling_outputs import CausalLMOutput
+import torch.nn as nn
+import torch.nn.functional as F
+
 class MinimalLLMForCausalLM(PreTrainedModel, GenerationMixin):
     config_class = MinimalLLMConfig
     base_model_prefix = "model"