Upload 8 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model/tokenizer.json filter=lfs diff=lfs merge=lfs -text

.streamlit/config.toml

@@ -0,0 +1,6 @@
+[theme]
+primaryColor="#d92525"
+backgroundColor="#f2f2f2"
+secondaryBackgroundColor="#cacaca"
+textColor="#16232e"
+font="serif"

app.py

@@ -0,0 +1,28 @@
+import streamlit as st
+import torch
+from transformers import pipeline
+
+st.set_page_config(page_title="Vietnamese Legal Question Answering", page_icon="🧊", layout="centered", initial_sidebar_state="collapsed")
+
+@st.cache_data
+def load_model(model_path):
+    device = 0 if torch.cuda.is_available() else -1
+    question_answerer = pipeline("question-answering", model=model_path, device=device)
+    return question_answerer
+
+def get_answer(model, context, question):
+    return model(context=context, question=question, max_answer_len=512)
+
+if 'model' not in st.session_state:
+    st.session_state.model = load_model(model_path='./models/vi-mrc-large/model')
+
+st.markdown("<h1 style='text-align: center;'>Vietnamese Legal Question Answering</h1>", unsafe_allow_html=True)
+
+context = st.text_area(label='Vietnamese Legal Documents/context:', placeholder='Enter your Vietnamese legal document here...', height=300)
+question = st.text_area(label='Question about this Vietnamese Legal Documents:', placeholder='Enter your question about this Vietnamese Legal Documents here...', height=100)
+
+btn_answer = st.button(label='Answer')
+
+if btn_answer:
+    answer = get_answer(model=st.session_state.model, context=context, question=question)
+    st.success(f"{answer['answer']}")

model/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "nguyenvulebinh/vi-mrc-large",
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad7c0e2a5d215bc2ed71657191a8d78f3e1dfbc4ea033b06b0db4c06ee3e060
+size 2235420048

model/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

model/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdc3a60b9984918cef056322135d19f0ffa477c8df479cca065bcbfb0dbbc8cd
+size 17083020

model/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3580c20056a294519b2f01b0ce004bf9373facc3bb1a2462ffbc08afeba7ca77
+size 4920