Initial commit from mrm8488
Browse files- .gitattributes +1 -0
- config.json +42 -0
- merges.txt +0 -0
- nbest_predictions_.json +3 -0
- predictions_.json +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*_.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mrm8488/longformer-base-4096-spanish",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"attention_window": [
|
8 |
+
512,
|
9 |
+
512,
|
10 |
+
512,
|
11 |
+
512,
|
12 |
+
512,
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512
|
20 |
+
],
|
21 |
+
"bos_token_id": 0,
|
22 |
+
"classifier_dropout": null,
|
23 |
+
"eos_token_id": 2,
|
24 |
+
"gradient_checkpointing": false,
|
25 |
+
"hidden_act": "gelu",
|
26 |
+
"hidden_dropout_prob": 0.1,
|
27 |
+
"hidden_size": 768,
|
28 |
+
"initializer_range": 0.02,
|
29 |
+
"intermediate_size": 3072,
|
30 |
+
"layer_norm_eps": 1e-05,
|
31 |
+
"max_position_embeddings": 4098,
|
32 |
+
"model_type": "roberta",
|
33 |
+
"num_attention_heads": 12,
|
34 |
+
"num_hidden_layers": 12,
|
35 |
+
"pad_token_id": 1,
|
36 |
+
"position_embedding_type": "absolute",
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.16.0.dev0",
|
39 |
+
"type_vocab_size": 1,
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 50265
|
42 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
nbest_predictions_.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:531fc490e1a81b4ba5a287c84ff9f216e2de29eb6ddc4c9688a59e109d41a089
|
3 |
+
size 9068137
|
predictions_.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06f78d8d89e20ee337edb1f9dd63fdb83f01f91d3a44c1c67d4a5f8d34d13c57
|
3 |
+
size 159170
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bfa6a9919be80613c6fa53ccb47f091dd9cd0e0324fc6e8a307b37f5a69fb61
|
3 |
+
size 507349745
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "trim_offsets": true, "special_tokens_map_file": null, "name_or_path": "mrm8488/longformer-base-4096-spanish", "do_lower_case": false, "tokenizer_file": "/root/.cache/huggingface/transformers/b5855f13c9a61de4b125a46aecb50ce5e6fce42bb015b9a9878ecfd3b208134a.77e23835743bc2dbd73aadbb18fd789f80874582c38c5ceef526bad321de9250", "tokenizer_class": "RobertaTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c47689924e3db7920fa1e198669404209d46c9b2582cd045d9c00f8afc2ebb07
|
3 |
+
size 1711
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|