up

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": "4.27.0.dev0",
+  "type_vocab_size": 16,
+  "use_cache": true,
+  "vocab_size": 1124
+}

pytorch_model.bin.index.v2.json

@@ -0,0 +1,95 @@
+{
+  "metadata": {
+    "total_size": 355812
+  },
+  "weight_map": {
+    "embeddings.LayerNorm.bias": "pytorch_model.v2-00004-of-00006.bin",
+    "embeddings.LayerNorm.weight": "pytorch_model.v2-00004-of-00006.bin",
+    "embeddings.position_embeddings.weight": "pytorch_model.v2-00003-of-00006.bin",
+    "embeddings.position_ids": "pytorch_model.v2-00001-of-00006.bin",
+    "embeddings.token_type_embeddings.weight": "pytorch_model.v2-00004-of-00006.bin",
+    "embeddings.word_embeddings.weight": "pytorch_model.v2-00002-of-00006.bin",
+    "encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.0.attention.output.dense.bias": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.0.attention.output.dense.weight": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.0.attention.self.key.bias": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.0.attention.self.key.weight": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.0.attention.self.query.bias": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.0.attention.self.query.weight": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.0.attention.self.value.bias": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.0.attention.self.value.weight": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.0.intermediate.dense.bias": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.0.intermediate.dense.weight": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.0.output.LayerNorm.bias": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.0.output.LayerNorm.weight": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.0.output.dense.bias": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.0.output.dense.weight": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.1.attention.output.dense.bias": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.1.attention.output.dense.weight": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.1.attention.self.key.bias": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.1.attention.self.key.weight": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.1.attention.self.query.bias": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.1.attention.self.query.weight": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.1.attention.self.value.bias": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.1.attention.self.value.weight": "pytorch_model.v2-00004-of-00006.bin",
+    "encoder.layer.1.intermediate.dense.bias": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.1.intermediate.dense.weight": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.1.output.LayerNorm.bias": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.1.output.LayerNorm.weight": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.1.output.dense.bias": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.1.output.dense.weight": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.2.attention.output.dense.bias": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.2.attention.output.dense.weight": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.2.attention.self.key.bias": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.2.attention.self.key.weight": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.2.attention.self.query.bias": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.2.attention.self.query.weight": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.2.attention.self.value.bias": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.2.attention.self.value.weight": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.2.intermediate.dense.bias": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.2.intermediate.dense.weight": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.2.output.LayerNorm.bias": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.2.output.LayerNorm.weight": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.2.output.dense.bias": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.2.output.dense.weight": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.3.attention.output.dense.bias": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.3.attention.output.dense.weight": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.3.attention.self.key.bias": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.3.attention.self.key.weight": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.3.attention.self.query.bias": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.3.attention.self.query.weight": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.3.attention.self.value.bias": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.3.attention.self.value.weight": "pytorch_model.v2-00005-of-00006.bin",
+    "encoder.layer.3.intermediate.dense.bias": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.3.intermediate.dense.weight": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.3.output.LayerNorm.bias": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.3.output.LayerNorm.weight": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.3.output.dense.bias": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.3.output.dense.weight": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.4.attention.output.dense.bias": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.4.attention.output.dense.weight": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.4.attention.self.key.bias": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.4.attention.self.key.weight": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.4.attention.self.query.bias": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.4.attention.self.query.weight": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.4.attention.self.value.bias": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.4.attention.self.value.weight": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.4.intermediate.dense.bias": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.4.intermediate.dense.weight": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.4.output.LayerNorm.bias": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.4.output.LayerNorm.weight": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.4.output.dense.bias": "pytorch_model.v2-00006-of-00006.bin",
+    "encoder.layer.4.output.dense.weight": "pytorch_model.v2-00006-of-00006.bin",
+    "pooler.dense.bias": "pytorch_model.v2-00006-of-00006.bin",
+    "pooler.dense.weight": "pytorch_model.v2-00006-of-00006.bin"
+  }
+}

pytorch_model.v2-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ee4627d757583832992a63346937ccf2cdcb9803469eea0151c0bd45cf9ed5
+size 5043

pytorch_model.v2-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86fca77d0005e44dc939016d7f5f39be5b0fd67c808b32ea10891c957c75e56c
+size 144819

pytorch_model.v2-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b14eb0fd155291e1536a79d3375ae3256d8ecee1fa3ccce12f296ecf95d096
+size 66483

pytorch_model.v2-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83944a43c65517d03be60e82496ce14560be5c011918cda2d04d75fb210ae0b7
+size 56246

pytorch_model.v2-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea53c03ac535a24adc6a14fa541926be6b9a6f548184e2d7ba1405ca94026685
+size 59169

pytorch_model.v2-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c29b1132930b34ecc532f29a9f2cd37ecea0255df1f51b329a8346613064da5
+size 55137