add model

README.md

@@ -1,3 +1,27 @@
 ---
-license: apache-2.0
+language: 
+- vi
+- vn
+- en
+tags:
+- question-answering
+- pytorch
+datasets:
+- squad
+pipeline_tag: question-answering 
+metrics:
+- squad
 ---
+  
+```python
+from transformers import pipeline
+model_checkpoint = "aicryptogroup/distill-xlm-mrc"
+nlp = pipeline('question-answering', model=model_checkpoint,
+                   tokenizer=model_checkpoint)
+QA_input = {
+  'question': "what is the capital of Vietnam",
+  '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."
+}
+res = nlp(QA_input)
+print('pipeline: {}'.format(res))
+

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "dmec-mrc-base",
+  "architectures": [
+    "MRCQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 49576
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c1fc8ab7c8ed75cf9666ec217fcfb0aeb166d87403791ca374cf1631b0d29d5
+size 162202097

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e4c79af3897cbd1628364e90dd09303605625130b65f3524d4a84747f06e59
+size 1102832

special_tokens_map.json

@@ -0,0 +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_config.json

@@ -0,0 +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"}