Upload model files
Browse files- README.md +22 -0
- config.json +31 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: en
|
3 |
+
---
|
4 |
+
|
5 |
+
# Sparse BERT base model fine tuned to MNLI without classifier layer (uncased)
|
6 |
+
|
7 |
+
Fine tuned sparse BERT base to MNLI (GLUE Benchmark) task from [bert-base-uncased-sparse-70-unstructured](https://huggingface.co/Intel/bert-base-uncased-sparse-70-unstructured).
|
8 |
+
<br>
|
9 |
+
This model doesn't have a classifier layer to enable easier loading of the model for training to other downstream tasks.
|
10 |
+
In all the other layers this model is similar to [bert-base-uncased-mnli-sparse-70-unstructured](https://huggingface.co/Intel/bert-base-uncased-mnli-sparse-70-unstructured).
|
11 |
+
<br><br>
|
12 |
+
Note: This model requires `transformers==2.10.0`
|
13 |
+
|
14 |
+
## Evaluation Results
|
15 |
+
Matched: 82.5%
|
16 |
+
Mismatched: 83.3%
|
17 |
+
|
18 |
+
This model can be further fine-tuned to other tasks and achieve the following evaluation results:
|
19 |
+
|
20 |
+
| Task | QQP (Acc/F1) | QNLI (Acc) | SST-2 (Acc) | STS-B (Pears/Spear) | SQuADv1.1 (Acc/F1) |
|
21 |
+
|------|--------------|------------|-------------|---------------------|--------------------|
|
22 |
+
| | 90.2/86.7 | 90.3 | 91.5 | 88.9/88.6 | 80.5/88.2 |
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForSequenceClassification"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"finetuning_task": "mnli",
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"label2id": {
|
19 |
+
"LABEL_0": 0,
|
20 |
+
"LABEL_1": 1,
|
21 |
+
"LABEL_2": 2
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "bert",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"vocab_size": 30522
|
31 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:955735e9502bbbb96f358a3db7af654d4cd272cb0fa5390f39369ee060d8084d
|
3 |
+
size 438008068
|
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_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, "name_or_path": "bert-base-uncased"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|