mathildeparlo
commited on
Commit
•
efcd37a
1
Parent(s):
c38e216
Training in progress, epoch 1
Browse files- config.json +15 -22
- pytorch_model.bin +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +2 -2
- training_args.bin +2 -2
- vocab.txt +0 -0
config.json
CHANGED
@@ -1,31 +1,24 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
|
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"hidden_dropout_prob": 0.1,
|
11 |
-
"hidden_size": 768,
|
12 |
"initializer_range": 0.02,
|
13 |
-
"intermediate_size": 3072,
|
14 |
-
"layer_norm_eps": 1e-12,
|
15 |
"max_position_embeddings": 512,
|
16 |
-
"model_type": "
|
17 |
-
"
|
18 |
-
"
|
19 |
"pad_token_id": 0,
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"pooler_type": "first_token_transform",
|
25 |
-
"position_embedding_type": "absolute",
|
26 |
"torch_dtype": "float32",
|
27 |
"transformers_version": "4.34.1",
|
28 |
-
"
|
29 |
-
"use_cache": true,
|
30 |
-
"vocab_size": 119547
|
31 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
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 |
"torch_dtype": "float32",
|
22 |
"transformers_version": "4.34.1",
|
23 |
+
"vocab_size": 30522
|
|
|
|
|
24 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e53c85f633a6ab1a0255e78349ac9c6e7c83356d73b7e331b7751567da623e41
|
3 |
+
size 265491554
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -43,13 +43,13 @@
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
-
"do_lower_case":
|
47 |
"mask_token": "[MASK]",
|
48 |
"model_max_length": 512,
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
51 |
"strip_accents": null,
|
52 |
"tokenize_chinese_chars": true,
|
53 |
-
"tokenizer_class": "
|
54 |
"unk_token": "[UNK]"
|
55 |
}
|
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
"mask_token": "[MASK]",
|
48 |
"model_max_length": 512,
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
51 |
"strip_accents": null,
|
52 |
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
"unk_token": "[UNK]"
|
55 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7a9a6c584d89b4a562978f7856ba746e789f0c42881d913f66c4633245bb520
|
3 |
+
size 4472
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|