Upload model

MyModel.py

@@ -1,12 +1,15 @@
 
 from transformers import PreTrainedModel
-from .MyConfig import MnistConfig
+from .MyConfig import MnistConfig # local import
 from torch import nn
 import torch.nn.functional as F
 
 class MnistModel(PreTrainedModel):
+    # pass the previously defined config class to the model
     config_class = MnistConfig
+
     def __init__(self, config):
+        # instantiate the model using the configuration
         super().__init__(config)
         # use the config to instantiate our model
         self.conv1 = nn.Conv2d(1, config.conv1, kernel_size=5)
@@ -15,15 +18,19 @@ class MnistModel(PreTrainedModel):
         self.fc1 = nn.Linear(320, 50)
         self.fc2 = nn.Linear(50, 10)
         self.softmax = nn.Softmax(dim=-1)
+        self.criterion = nn.CrossEntropyLoss()
     def forward(self, x,labels=None):
+        # the labels parameter allows us to finetune our model
+        # with the Trainer API easily
         x = F.relu(F.max_pool2d(self.conv1(x), 2))
         x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
         x = x.view(-1, 320)
         x = F.relu(self.fc1(x))
         x = F.dropout(x, training=self.training)
         x = self.fc2(x)
-        output = self.softmax(x)
+        logits = self.softmax(x)
         if labels != None :
-          print("continue training script here")
-
-        return output
+          # this will make your AI compatible with the trainer API
+          loss = self.criterion(logits, labels)
+          return {"loss": loss, "logits": logits}
+        return logits

config.json

@@ -1,9 +1,14 @@
 {
+  "architectures": [
+    "MnistModel"
+  ],
   "auto_map": {
-    "AutoConfig": "MyConfig.MnistConfig"
+    "AutoConfig": "MyConfig.MnistConfig",
+    "AutoModelForImageClassification": "MyModel.MnistModel"
   },
   "conv1": 10,
   "conv2": 20,
   "model_type": "MobileNetV1",
+  "torch_dtype": "float32",
   "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eee7d5198f4d57968bd06755727c4e89cd627b1b5fa7e0bfa42cf5a3bcd6697
+oid sha256:7498727b72f4e20562223eb879e58b9410e06c37a678be0960dfb3650b11dd27
 size 87976