Add sharded checkpoints

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "explosion-testing/bert-test-caching",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 37,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 5,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 16,
+  "use_cache": true,
+  "vocab_size": 1024
+}

model.safetensors.index.json

@@ -0,0 +1,94 @@
+{
+  "metadata": {
+    "total_size": 338916
+  },
+  "weight_map": {
+    "embeddings.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "embeddings.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "embeddings.position_embeddings.weight": "model-00002-of-00003.safetensors",
+    "embeddings.token_type_embeddings.weight": "model-00002-of-00003.safetensors",
+    "embeddings.word_embeddings.weight": "model-00001-of-00003.safetensors",
+    "encoder.layer.0.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "encoder.layer.0.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "encoder.layer.0.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "encoder.layer.0.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "encoder.layer.0.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "encoder.layer.0.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "encoder.layer.0.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "encoder.layer.0.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "encoder.layer.0.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "encoder.layer.0.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "encoder.layer.0.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "encoder.layer.0.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "encoder.layer.0.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "encoder.layer.0.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "encoder.layer.0.output.dense.bias": "model-00002-of-00003.safetensors",
+    "encoder.layer.0.output.dense.weight": "model-00002-of-00003.safetensors",
+    "encoder.layer.1.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "encoder.layer.1.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "encoder.layer.1.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "encoder.layer.1.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "encoder.layer.1.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "encoder.layer.1.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "encoder.layer.1.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "encoder.layer.1.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "encoder.layer.1.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "encoder.layer.1.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "encoder.layer.1.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "encoder.layer.1.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "encoder.layer.1.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.1.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.1.output.dense.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.1.output.dense.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.2.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.2.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.2.attention.output.dense.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.2.attention.output.dense.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.2.attention.self.key.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.2.attention.self.key.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.2.attention.self.query.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.2.attention.self.query.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.2.attention.self.value.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.2.attention.self.value.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.2.intermediate.dense.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.2.intermediate.dense.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.2.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.2.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.2.output.dense.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.2.output.dense.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.3.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.3.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.3.attention.output.dense.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.3.attention.output.dense.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.3.attention.self.key.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.3.attention.self.key.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.3.attention.self.query.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.3.attention.self.query.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.3.attention.self.value.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.3.attention.self.value.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.3.intermediate.dense.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.3.intermediate.dense.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.3.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.3.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.3.output.dense.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.3.output.dense.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.4.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.4.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.4.attention.output.dense.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.4.attention.output.dense.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.4.attention.self.key.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.4.attention.self.key.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.4.attention.self.query.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.4.attention.self.query.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.4.attention.self.value.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.4.attention.self.value.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.4.intermediate.dense.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.4.intermediate.dense.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.4.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.4.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "encoder.layer.4.output.dense.bias": "model-00003-of-00003.safetensors",
+    "encoder.layer.4.output.dense.weight": "model-00003-of-00003.safetensors",
+    "pooler.dense.bias": "model-00003-of-00003.safetensors",
+    "pooler.dense.weight": "model-00003-of-00003.safetensors"
+  }
+}

pytorch_model.bin.index.json

@@ -0,0 +1,94 @@
+{
+  "metadata": {
+    "total_size": 338916
+  },
+  "weight_map": {
+    "embeddings.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "embeddings.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "embeddings.position_embeddings.weight": "pytorch_model-00002-of-00003.bin",
+    "embeddings.token_type_embeddings.weight": "pytorch_model-00002-of-00003.bin",
+    "embeddings.word_embeddings.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.0.attention.output.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.0.attention.output.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.0.attention.self.key.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.0.attention.self.key.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.0.attention.self.query.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.0.attention.self.query.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.0.attention.self.value.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.0.attention.self.value.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.0.intermediate.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.0.intermediate.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.0.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.0.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.0.output.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.0.output.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.1.attention.output.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.1.attention.output.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.1.attention.self.key.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.1.attention.self.key.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.1.attention.self.query.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.1.attention.self.query.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.1.attention.self.value.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.1.attention.self.value.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.1.intermediate.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.1.intermediate.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.1.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.1.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.1.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.1.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.2.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.2.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.2.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.2.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.2.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.2.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.2.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.2.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.2.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.2.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.2.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.2.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.2.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.2.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.3.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.3.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.3.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.3.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.3.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.3.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.3.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.3.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.3.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.3.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.3.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.3.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.3.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.3.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.4.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.4.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.4.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.4.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.4.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.4.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.4.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.4.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.4.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.4.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.4.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.4.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.4.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.4.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "pooler.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "pooler.dense.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}