anhtunguyen98
commited on
Commit
•
a3c5573
1
Parent(s):
4afe539
add model
Browse files- README.md +25 -1
- config.json +28 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
README.md
CHANGED
@@ -1,3 +1,27 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- vi
|
4 |
+
- vn
|
5 |
+
- en
|
6 |
+
tags:
|
7 |
+
- question-answering
|
8 |
+
- pytorch
|
9 |
+
datasets:
|
10 |
+
- squad
|
11 |
+
pipeline_tag: question-answering
|
12 |
+
metrics:
|
13 |
+
- squad
|
14 |
---
|
15 |
+
|
16 |
+
```python
|
17 |
+
from transformers import pipeline
|
18 |
+
model_checkpoint = "aicryptogroup/distill-xlm-mrc"
|
19 |
+
nlp = pipeline('question-answering', model=model_checkpoint,
|
20 |
+
tokenizer=model_checkpoint)
|
21 |
+
QA_input = {
|
22 |
+
'question': "what is the capital of Vietnam",
|
23 |
+
'context': "Keeping an ageless charm through centuries, Hanoi - the capital of Vietnam is famous not only for the Old Quarter with narrow and crowded streets but also for the nostalgic feeling that it brings. While Saigon is a young and modern city, the ancient Hanoi is still a true beholder of history."
|
24 |
+
}
|
25 |
+
res = nlp(QA_input)
|
26 |
+
print('pipeline: {}'.format(res))
|
27 |
+
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dmec-mrc-base",
|
3 |
+
"architectures": [
|
4 |
+
"MRCQuestionAnswering"
|
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": 384,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 1536,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 514,
|
18 |
+
"model_type": "roberta",
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.9.2",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 49576
|
28 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c1fc8ab7c8ed75cf9666ec217fcfb0aeb166d87403791ca374cf1631b0d29d5
|
3 |
+
size 162202097
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85e4c79af3897cbd1628364e90dd09303605625130b65f3524d4a84747f06e59
|
3 |
+
size 1102832
|
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": true}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": null, "name_or_path": "anhtunguyen98/xlm-base-vi-en", "sp_model_kwargs": {}, "tokenizer_class": "XLMRobertaTokenizer"}
|