Add tile-aligned pytorch_model, onnx, ir

bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41efed3c2f85e7d71d619c8f80b39b88eac754472d792bc52b1c59e33d5273e7
+size 177575143

checkpoint-21750-tilealigned/config.json

@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "/data1/vchua/tld-poc/bert-base-squadv1-local-hybrid-compiled",
+  "architectures": [
+    "NNCFNetwork"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "pruned_heads": {
+    "0": [
+      0,
+      2,
+      4,
+      5,
+      6,
+      7,
+      11
+    ],
+    "1": [
+      0,
+      2,
+      3,
+      5,
+      6,
+      7,
+      8
+    ],
+    "2": [
+      8,
+      4,
+      7
+    ],
+    "3": [
+      2,
+      4,
+      6
+    ],
+    "4": [
+      1,
+      2,
+      11
+    ],
+    "5": [
+      1,
+      2,
+      5,
+      6,
+      7,
+      11
+    ],
+    "6": [
+      0,
+      2,
+      3,
+      7,
+      10
+    ],
+    "7": [
+      1,
+      3,
+      6,
+      7,
+      11
+    ],
+    "8": [
+      0,
+      3,
+      4,
+      5,
+      8
+    ],
+    "9": [
+      1,
+      3,
+      4,
+      5,
+      7,
+      9,
+      10
+    ],
+    "10": [
+      1,
+      4,
+      5,
+      6,
+      7,
+      8
+    ],
+    "11": [
+      4,
+      5,
+      7,
+      8,
+      10,
+      11
+    ]
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-21750-tilealigned/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:502d61b24766935d2d0b196d147d27f1f98bb63acb74c00544ff492f201d0276
+size 353016429

checkpoint-21750-tilealigned/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8521138bce93eb71a564b5d4200616bc005419839e62416c0efced9b4ae30cda
+size 259744785

checkpoint-21750-tilealigned/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a94692d497d62f266652bbbc4a1a07abeff70560b00b87755fc4710f1be4ee3f
+size 14503

checkpoint-21750-tilealigned/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e602f6bb85fa11ee4dd91991bfc4d199ca92f7b80f61a8a792f4315172ceab0b
+size 623

checkpoint-21750-tilealigned/special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

checkpoint-21750-tilealigned/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/data1/vchua/tld-poc/bert-base-squadv1-local-hybrid-compiled", "tokenizer_class": "BertTokenizer"}

checkpoint-21750-tilealigned/trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08d9f173574b7831a17f3e025503da75a134a1ea02db1d3b657468f835161f03
+size 11398921

checkpoint-21750-tilealigned/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b97d5ad5c00837e2ab0e008d14c563eb384f79123ee707c385a7929abfb8d9
+size 3439

ir-tilealigned/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07454e37766e40482ab3f0207c80233686ec934c4e8b7161e5164ef6df430eee
+size 44591720

ir-tilealigned/mo.log

@@ -0,0 +1,30 @@
+Model Optimizer arguments:
+Common parameters:
+	- Path to the Input Model: 	/home/openvino/tile/hybrid-tile-aligned-int8-eval/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned.onnx
+	- Path for generated IR: 	/home/openvino/tile/hybrid-tile-aligned-int8-eval/ir
+	- IR output name: 	bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned
+	- Log level: 	ERROR
+	- Batch: 	Not specified, inherited from the model
+	- Input layers: 	Not specified, inherited from the model
+	- Output layers: 	Not specified, inherited from the model
+	- Input shapes: 	Not specified, inherited from the model
+	- Mean values: 	Not specified
+	- Scale values: 	Not specified
+	- Scale factor: 	Not specified
+	- Precision of IR: 	FP32
+	- Enable fusing: 	True
+	- Enable grouped convolutions fusing: 	True
+	- Move mean values to preprocess section: 	None
+	- Reverse input channels: 	False
+ONNX specific parameters:
+	- Inference Engine found in: 	/opt/intel/openvino/python/python3.6/openvino
+Inference Engine version: 	2021.4.2-3974-e2a469a3450-releases/2021/4
+Model Optimizer version: 	2021.4.2-3974-e2a469a3450-releases/2021/4
+[ WARNING ]  Convert data type of Parameter "input_ids" to int32
+[ WARNING ]  Convert data type of Parameter "attention_mask.1" to int32
+[ WARNING ]  Convert data type of Parameter "input.1" to int32
+[ SUCCESS ] Generated IR version 10 model.
+[ SUCCESS ] XML file: /home/openvino/tile/hybrid-tile-aligned-int8-eval/ir/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned.xml
+[ SUCCESS ] BIN file: /home/openvino/tile/hybrid-tile-aligned-int8-eval/ir/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned.bin
+[ SUCCESS ] Total execution time: 78.71 seconds. 
+[ SUCCESS ] Memory consumed: 1920 MB.