first commit

Browse files

Files changed (4) hide show

config.json +188 -0
pytorch_model.bin +3 -0
tokenizer_config.json +1 -0
vocab.txt +0 -0

config.json ADDED Viewed

	@@ -0,0 +1,188 @@

+{
+  "architectures": [
+    "NewBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "decompose_qk": false,
+  "decompose_vo": false,
+  "do_distill": true,
+  "do_emb_distill": false,
+  "do_layer_distill": true,
+  "do_mha_distill": false,
+  "do_mha_layer_distill": false,
+  "finetuning_task": "sst-2",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_attentions": true,
+  "output_hidden_states": true,
+  "pad_token_id": 0,
+  "pruned_heads": {
+    "0": [
+      0,
+      4,
+      5,
+      6,
+      7,
+      8,
+      9
+    ],
+    "1": [
+      0,
+      1,
+      2,
+      3,
+      4,
+      5,
+      6,
+      7,
+      8,
+      9,
+      10,
+      11
+    ],
+    "2": [
+      0,
+      1,
+      2,
+      3,
+      4,
+      5,
+      6,
+      7,
+      8,
+      9,
+      10,
+      11
+    ],
+    "3": [
+      0,
+      1,
+      2,
+      3,
+      4,
+      5,
+      6,
+      7,
+      8,
+      9,
+      10,
+      11
+    ],
+    "4": [
+      0,
+      1,
+      2,
+      3,
+      4,
+      5,
+      6,
+      7,
+      8,
+      9,
+      10,
+      11
+    ],
+    "5": [
+      0,
+      1,
+      2,
+      3,
+      4,
+      5,
+      6,
+      7,
+      8,
+      9,
+      10,
+      11
+    ],
+    "6": [
+      0,
+      1,
+      2,
+      3,
+      4,
+      6,
+      7,
+      8,
+      10,
+      11
+    ],
+    "7": [
+      0,
+      1,
+      2,
+      3,
+      4,
+      5,
+      6,
+      7,
+      8,
+      9,
+      10,
+      11
+    ],
+    "8": [
+      0,
+      1,
+      2,
+      3,
+      4,
+      5,
+      6,
+      7,
+      8,
+      10
+    ],
+    "9": [
+      0,
+      1,
+      3,
+      4,
+      6,
+      7,
+      8,
+      9,
+      10,
+      11
+    ],
+    "10": [
+      0,
+      1,
+      2,
+      3,
+      5,
+      6,
+      7,
+      8,
+      10,
+      11
+    ],
+    "11": [
+      0,
+      1,
+      2,
+      3,
+      5,
+      6,
+      7,
+      8,
+      9,
+      11
+    ]
+  },
+  "qk_denominator": "ori",
+  "sephidden_pruned": false,
+  "transform_embedding": false,
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:21ce13174880a6b439ec788cbc77c8b6f5a4be81734c90b7878a3592fd1ae630
+size 116237287

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"do_lower_case": true, "model_max_length": 512}

vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff