commit files to HF hub

.gitattributes

@@ -30,3 +30,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "hf-internal-testing/tiny-random-bert-sharded",
+  "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": "4.23.0.dev0",
+  "type_vocab_size": 16,
+  "use_cache": true,
+  "vocab_size": 1124
+}

model-00001-of-00005.safetensors

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

model-00002-of-00005.safetensors

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

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b601275d5cf98dae763b61e27102fc2f9ead3c18eb801e099880557d338614b
+size 101482

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68641a25e97dc737b95f648cbf9777d1e08e1fe1ef6537c4e6e125fa9d7e1e7e
+size 105310

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21a9e02c5075a5ff5c4be6e6d0e4ca3d8c2d80159286696a504762674ae44d14
+size 9919

model.safetensors.index.json

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

pytorch_model-00001-of-00005.bin

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