BoDong commited on
Commit
6ceffc4
1 Parent(s): 413744d

upload the model

Browse files
README.md CHANGED
@@ -1,3 +1,19 @@
1
  ---
2
  license: apache-2.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
  ---
4
+
5
+ # Sparse DISTILBERT model (uncased)
6
+
7
+ Finetuned model pruned to 1:4 structured sparsity.
8
+
9
+ ## Intended Use
10
+
11
+ The model can be used for inference with sparsity optimization.
12
+ For further details on the model and its usage will be soon available.
13
+
14
+ ## Evaluation Results
15
+ We get the following results on the SQuADv1.1 tasks development set:
16
+
17
+ | Task | SQuADv1.1 (F1) |
18
+ |------|----------------|
19
+ | | 87.00 |
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Intel/distilbert-base-uncased-squadv1.1-sparse-80-1X4-block",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForQuestionAnswering"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": false,
20
+ "tie_weights_": true,
21
+ "transformers_version": "4.6.1",
22
+ "vocab_size": 30522
23
+ }
eval_predictions.json ADDED
The diff for this file is too large to render. See raw diff
 
eval_results.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.0,
3
+ "eval_samples": 10784,
4
+ "exact_match": 79.36613055818354,
5
+ "f1": 87.02605927129457
6
+ }
int8-model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deb627f2c83abc7d7d49a5f9a8f604e007da86238dbe79c3103f3d02fcb1ea0d
3
+ size 138535109
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09ac080bf2e006ac3ab7f0c63d2060d7bb2d76948e9b1bfbf2e80dfda014527d
3
+ size 265497077
sparse_int8_ir/conf.yaml ADDED
The diff for this file is too large to render. See raw diff
 
sparse_int8_ir/model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36e078488db499688448c1c53f338322618120f60b3a80385c68ce44cac0457e
3
+ size 138383760
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
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"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff