upload the model

README.md

@@ -1,3 +1,19 @@
 ---
 license: apache-2.0
 ---
+
+# Sparse DISTILBERT model (uncased)
+
+Finetuned model pruned to 1:4 structured sparsity.
+
+## Intended Use
+
+The model can be used for inference with sparsity optimization.
+For further details on the model and its usage will be soon available.
+
+## Evaluation Results
+We get the following results on the SQuADv1.1 tasks development set:
+
+| Task | SQuADv1.1 (F1) |
+|------|----------------|
+|      |      87.00     |

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "Intel/distilbert-base-uncased-squadv1.1-sparse-80-1X4-block",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForQuestionAnswering"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.6.1",
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 8.0,
+    "eval_samples": 10784,
+    "exact_match": 79.36613055818354,
+    "f1": 87.02605927129457
+}

int8-model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb627f2c83abc7d7d49a5f9a8f604e007da86238dbe79c3103f3d02fcb1ea0d
+size 138535109

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ac080bf2e006ac3ab7f0c63d2060d7bb2d76948e9b1bfbf2e80dfda014527d
+size 265497077

sparse_int8_ir/model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e078488db499688448c1c53f338322618120f60b3a80385c68ce44cac0457e
+size 138383760

special_tokens_map.json

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

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": "bert-base-uncased"}