Improved supervisor with deepset/tinyroberta-6l-768d
Browse files- config.json +16 -11
- merges.txt +0 -0
- special_tokens_map.json +13 -5
- tf_model.h5 +2 -2
- tokenizer.json +2 -2
- tokenizer_config.json +15 -14
- training.json +6 -6
- vocab.json +0 -0
config.json
CHANGED
@@ -1,25 +1,30 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "deepset/
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
7 |
"classifier_dropout": null,
|
|
|
8 |
"gradient_checkpointing": false,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
-
"hidden_size":
|
12 |
"initializer_range": 0.02,
|
13 |
-
"intermediate_size":
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
|
|
|
|
17 |
"num_attention_heads": 12,
|
18 |
-
"num_hidden_layers":
|
19 |
-
"pad_token_id":
|
20 |
"position_embedding_type": "absolute",
|
|
|
21 |
"transformers_version": "4.24.0",
|
22 |
-
"type_vocab_size":
|
23 |
"use_cache": true,
|
24 |
-
"vocab_size":
|
25 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "deepset/tinyroberta-6l-768d",
|
3 |
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
"gradient_checkpointing": false,
|
11 |
"hidden_act": "gelu",
|
12 |
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"language": "english",
|
17 |
+
"layer_norm_eps": 1e-05,
|
18 |
+
"max_position_embeddings": 514,
|
19 |
+
"model_type": "roberta",
|
20 |
+
"name": "Roberta",
|
21 |
"num_attention_heads": 12,
|
22 |
+
"num_hidden_layers": 6,
|
23 |
+
"pad_token_id": 1,
|
24 |
"position_embedding_type": "absolute",
|
25 |
+
"torch_dtype": "float32",
|
26 |
"transformers_version": "4.24.0",
|
27 |
+
"type_vocab_size": 1,
|
28 |
"use_cache": true,
|
29 |
+
"vocab_size": 50265
|
30 |
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,15 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
}
|
tf_model.h5
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 sha256:176c061a588de46a0826c40dcb6e44480de3cc6e5cd337cd4f5f285e0438281f
|
3 |
+
size 328629336
|
tokenizer.json
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 sha256:1f325de61b2d8f48f2580c234ef57f927ffb952ea8617a9820559ec6b7b687e5
|
3 |
+
size 2108717
|
tokenizer_config.json
CHANGED
@@ -1,17 +1,18 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
|
|
|
|
7 |
"max_len": 384,
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"pad_token": "
|
11 |
-
"sep_token": "
|
12 |
-
"special_tokens_map_file":
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"unk_token": "[UNK]"
|
17 |
}
|
|
|
1 |
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"do_lower_case": false,
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"errors": "replace",
|
8 |
+
"mask_token": "<mask>",
|
9 |
"max_len": 384,
|
10 |
+
"model_max_length": 512,
|
11 |
+
"name_or_path": "deepset/tinyroberta-6l-768d",
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"special_tokens_map_file": null,
|
15 |
+
"tokenizer_class": "RobertaTokenizer",
|
16 |
+
"trim_offsets": true,
|
17 |
+
"unk_token": "<unk>"
|
|
|
18 |
}
|
training.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
"epochs": 2,
|
3 |
"learning_rate": 1e-05,
|
4 |
-
"model_name": "deepset/
|
5 |
"evaluation": [
|
6 |
-
0.
|
7 |
-
0.
|
8 |
-
0.
|
9 |
-
0.
|
10 |
-
0.
|
11 |
]
|
12 |
}
|
|
|
1 |
{
|
2 |
"epochs": 2,
|
3 |
"learning_rate": 1e-05,
|
4 |
+
"model_name": "deepset/tinyroberta-6l-768d",
|
5 |
"evaluation": [
|
6 |
+
0.001422734576696505,
|
7 |
+
0.001509308632540951,
|
8 |
+
0.9986003600680058,
|
9 |
+
0.9986481850885693,
|
10 |
+
0.011450733192732265
|
11 |
]
|
12 |
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|