upload

bert/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "hf-internal-testing/tiny-random-bert",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "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": "4.18.0.dev0",
+  "type_vocab_size": 16,
+  "use_cache": true,
+  "vocab_size": 1124
+}

bert/pytorch_model-00001-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd420eb358a99a5150cb374dec757373d5cc91b0b460ac2eb2d3bfb22888dcf6
+size 4843

bert/pytorch_model-00002-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a37b91bed13a298130eb8a8a8ae19477cc5ddb6ebd0ee89abe109cb3474d23a7
+size 144683

bert/pytorch_model-00003-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c1ab90263be374c6c66cc3f368b943585fc8f40e59571c6c98e1664edea9690
+size 105443

bert/pytorch_model-00004-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f069b4362265840846cc44f3ad125893917fcaa23afa41bf5f7de0ab680969cc
+size 116599

bert/pytorch_model-00005-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7fb234990f8f085471fe63b90c1039a48dc904762962d21928764fb91ee9234
+size 11159

bert/pytorch_model.bin.index.json

@@ -0,0 +1,96 @@
+{
+  "dtype": "int64",
+  "metadata": {
+    "total_size": 355812
+  },
+  "weight_map": {
+    "embeddings.LayerNorm.bias": "pytorch_model-00003-of-00005.bin",
+    "embeddings.LayerNorm.weight": "pytorch_model-00003-of-00005.bin",
+    "embeddings.position_embeddings.weight": "pytorch_model-00003-of-00005.bin",
+    "embeddings.position_ids": "pytorch_model-00001-of-00005.bin",
+    "embeddings.token_type_embeddings.weight": "pytorch_model-00003-of-00005.bin",
+    "embeddings.word_embeddings.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.0.attention.output.dense.bias": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.0.attention.output.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.0.attention.self.key.bias": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.0.attention.self.key.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.0.attention.self.query.bias": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.0.attention.self.query.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.0.attention.self.value.bias": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.0.attention.self.value.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.0.intermediate.dense.bias": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.0.intermediate.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.0.output.LayerNorm.bias": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.0.output.LayerNorm.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.0.output.dense.bias": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.0.output.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.1.attention.output.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.1.attention.output.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.1.attention.self.key.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.1.attention.self.key.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.1.attention.self.query.bias": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.1.attention.self.query.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.layer.1.attention.self.value.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.1.attention.self.value.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.1.intermediate.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.1.intermediate.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.1.output.LayerNorm.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.1.output.LayerNorm.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.1.output.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.1.output.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.2.attention.output.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.2.attention.output.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.2.attention.self.key.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.2.attention.self.key.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.2.attention.self.query.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.2.attention.self.query.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.2.attention.self.value.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.2.attention.self.value.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.2.intermediate.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.2.intermediate.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.2.output.LayerNorm.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.2.output.LayerNorm.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.2.output.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.2.output.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.3.attention.output.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.3.attention.output.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.3.attention.self.key.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.3.attention.self.key.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.3.attention.self.query.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.3.attention.self.query.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.3.attention.self.value.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.3.attention.self.value.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.3.intermediate.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.3.intermediate.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.3.output.LayerNorm.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.3.output.LayerNorm.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.3.output.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.3.output.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.4.attention.output.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.4.attention.output.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.4.attention.self.key.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.4.attention.self.key.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.4.attention.self.query.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.4.attention.self.query.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.4.attention.self.value.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.4.attention.self.value.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.4.intermediate.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.4.intermediate.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.layer.4.output.LayerNorm.bias": "pytorch_model-00005-of-00005.bin",
+    "encoder.layer.4.output.LayerNorm.weight": "pytorch_model-00005-of-00005.bin",
+    "encoder.layer.4.output.dense.bias": "pytorch_model-00005-of-00005.bin",
+    "encoder.layer.4.output.dense.weight": "pytorch_model-00005-of-00005.bin",
+    "pooler.dense.bias": "pytorch_model-00005-of-00005.bin",
+    "pooler.dense.weight": "pytorch_model-00005-of-00005.bin"
+  }
+}