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
+}

model.safetensors.index.v2.json

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

model.v2-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3b6b2ce753775fddfdedda5bc4774bf6af48513e16ef9c8f4e7823a1d3f205e
+size 4218

model.v2-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc90ac0fd83f2036f181ebdfca9090667509a9fae17fe10cbd3f2afc3a5e2677
+size 144008

model.v2-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98df52a9bf9e73db6f149561f6ae26335927ea6fd2f18b06b16567ad1c3417f
+size 65674

model.v2-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09781a57fa62ff9446e223d030f5757b030f72c7cd1a38d0729cd438600c8165
+size 49609

model.v2-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9357d328aa5f42dcc389387f777e601691e1331b8b355aab35256600bd74722c
+size 52725

model.v2-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ad5642d854c7b701e120360fe9de68d05dc3f80d0105781e47e552ce4f8ea2
+size 48714