victorbahlangene
commited on
Commit
•
095b3a7
1
Parent(s):
19f68e2
3rd part xlnet model
Browse files- .gitignore +1 -0
- config.json +44 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +19 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +26 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlnet-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"XLNetForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attn_type": "bi",
|
7 |
+
"bi_data": false,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"clamp_len": -1,
|
10 |
+
"d_head": 64,
|
11 |
+
"d_inner": 3072,
|
12 |
+
"d_model": 768,
|
13 |
+
"dropout": 0.1,
|
14 |
+
"end_n_top": 5,
|
15 |
+
"eos_token_id": 2,
|
16 |
+
"ff_activation": "gelu",
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"layer_norm_eps": 1e-12,
|
19 |
+
"mem_len": null,
|
20 |
+
"model_type": "xlnet",
|
21 |
+
"n_head": 12,
|
22 |
+
"n_layer": 12,
|
23 |
+
"pad_token_id": 5,
|
24 |
+
"problem_type": "single_label_classification",
|
25 |
+
"reuse_len": null,
|
26 |
+
"same_length": false,
|
27 |
+
"start_n_top": 5,
|
28 |
+
"summary_activation": "tanh",
|
29 |
+
"summary_last_dropout": 0.1,
|
30 |
+
"summary_type": "last",
|
31 |
+
"summary_use_proj": true,
|
32 |
+
"task_specific_params": {
|
33 |
+
"text-generation": {
|
34 |
+
"do_sample": true,
|
35 |
+
"max_length": 250
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.24.0",
|
40 |
+
"untie_r": true,
|
41 |
+
"use_mems_eval": true,
|
42 |
+
"use_mems_train": false,
|
43 |
+
"vocab_size": 32000
|
44 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fe6f473040980e8ef42f22cc86942e4464a3e2d359eed667e833fb2c40e5b29
|
3 |
+
size 469309853
|
special_tokens_map.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<eop>",
|
4 |
+
"<eod>"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"cls_token": "<cls>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"mask_token": {
|
10 |
+
"content": "<mask>",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<pad>",
|
17 |
+
"sep_token": "<sep>",
|
18 |
+
"unk_token": "<unk>"
|
19 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
|
3 |
+
size 798011
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<eop>",
|
4 |
+
"<eod>"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"cls_token": "<cls>",
|
8 |
+
"do_lower_case": false,
|
9 |
+
"eos_token": "</s>",
|
10 |
+
"keep_accents": false,
|
11 |
+
"mask_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "<mask>",
|
14 |
+
"lstrip": true,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"name_or_path": "xlnet-base-cased",
|
20 |
+
"pad_token": "<pad>",
|
21 |
+
"remove_space": true,
|
22 |
+
"sep_token": "<sep>",
|
23 |
+
"special_tokens_map_file": null,
|
24 |
+
"tokenizer_class": "XLNetTokenizer",
|
25 |
+
"unk_token": "<unk>"
|
26 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd0ebfd25d76064d491fa0f21f59c5ac3545993711fb762ce6db748e7fc2cc2c
|
3 |
+
size 3439
|