Add files
Browse files- README.md +13 -0
- config.json +22 -0
- pytorch_model.bin +3 -0
- rust_model.ot +3 -0
- saved_model.tar.gz +3 -0
- tf_model.h5 +3 -0
- tfjs.tar.gz +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: "en"
|
3 |
+
datasets:
|
4 |
+
- squad
|
5 |
+
metrics:
|
6 |
+
- squad
|
7 |
+
license: apache-2.0
|
8 |
+
---
|
9 |
+
|
10 |
+
# DistilBERT base cased distilled SQuAD
|
11 |
+
|
12 |
+
This model is a fine-tune checkpoint of [DistilBERT-base-cased](https://huggingface.co/distilbert-base-cased), fine-tuned using (a second step of) knowledge distillation on SQuAD v1.1.
|
13 |
+
This model reaches a F1 score of 87.1 on the dev set (for comparison, BERT bert-base-cased version reaches a F1 score of 88.7).
|
config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation": "gelu",
|
3 |
+
"architectures": [
|
4 |
+
"DistilBertForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.1,
|
7 |
+
"dim": 768,
|
8 |
+
"dropout": 0.1,
|
9 |
+
"hidden_dim": 3072,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"max_position_embeddings": 512,
|
12 |
+
"model_type": "distilbert",
|
13 |
+
"n_heads": 12,
|
14 |
+
"n_layers": 6,
|
15 |
+
"output_past": true,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"qa_dropout": 0.1,
|
18 |
+
"seq_classif_dropout": 0.2,
|
19 |
+
"sinusoidal_pos_embds": true,
|
20 |
+
"tie_weights_": true,
|
21 |
+
"vocab_size": 28996
|
22 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e10bdbc83fdbb975a430fc2148c85051e55bd288334deab18db58664ef0ea13
|
3 |
+
size 260793700
|
rust_model.ot
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a9f9b2f153ac9ff230aca4548fa3286be9d2f9ea4eb7e9169665b1a8e983f44
|
3 |
+
size 260795580
|
saved_model.tar.gz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7e26fe22fdeb23462ae6423fc04b7e4929212a49aa033c3a7b8f30c937c943f
|
3 |
+
size 241487391
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63ee5a0142067161ced524179c161c5026f47b53a34a946a5ad1a907fab35011
|
3 |
+
size 260894952
|
tfjs.tar.gz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e966858819faa94996263752a344fad68f858299ccdf27ccabe3d868c588186
|
3 |
+
size 241062466
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_lower_case": false
|
3 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|