Duplicate from BeMerciless/korean_malicious_comment

Co-authored-by: BeMerciless <[email protected]>

.gitattributes

@@ -0,0 +1,31 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,21 @@
+---
+title: Korean Malicious Comment
+emoji: ❌
+colorFrom: gray
+colorTo: pink
+sdk: gradio
+sdk_version: 3.5
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: BeMerciless/korean_malicious_comment
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+디지털스마트부산 자연어 처리 프로젝트
+동의대 분반 1조
+팀원: 박민석, 서민지, 이유나, 김선현
+
+This model is based on beomi/KcELECTRA-base.
+And datasets are from internet comments. 

app.py

@@ -0,0 +1,72 @@
+import gradio as gr
+import torch
+from transformers import AutoTokenizer
+
+#def greet(name):
+#    return "Hello " + name + "!!"
+
+def greet(sent,mode):
+  print("input_sent= " + sent)
+  if mode=='Malicious_comment':
+    pt_model ='best.pt'
+  if mode=='Economic_article':
+    pt_model ='best2.pt'
+  
+  
+  print(pt_model)
+  device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
+  print("device:",device)
+  
+  device = "cuda" if torch.cuda.is_available() else "cpu"
+  model = torch.load(pt_model, map_location=device)
+  print(model)
+
+  MODEL_NAME = "beomi/KcELECTRA-base" # hugging face 에 등록된 모델
+  tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+  
+  model.eval() # 평가
+
+  # 입력문장 토크나이징
+  tokenized_sent = tokenizer(
+      sent,
+      return_tensors="pt",
+      truncation=True, 
+      add_special_tokens=True, 
+      max_length=128
+      )
+
+  # 모델 위치 gpu이동
+  tokenized_sent.to(device)
+
+  # 예측
+  with torch.no_grad():
+    outputs = model(
+        input_ids=tokenized_sent["input_ids"],
+        attention_mask=tokenized_sent["attention_mask"],
+        token_type_ids=tokenized_sent["token_type_ids"],
+    )
+
+  # 결과
+  logits = outputs[0]   ## 마지막 노드에서 아무런 Activation Function을 거치지 않은 값을 Logit
+  logits = logits.detach().cpu()
+  result = logits.argmax(-1)
+  if mode=='Malicious_comment':
+    if result == 0:
+      result = sent + ">> 악성글로 판단됩니다. 조심하세요."
+      
+    elif result ==1:
+      result= sent + ">> 악의적인 내용이 보이지 않습니다."
+  elif mode=='Economic_article':
+    if result == 0:
+      result = "중립"
+    elif result == 1:
+      result = "긍정"
+    elif result == 2:
+      result = "부정"
+    
+    
+  return result
+intput="text"
+input2= gr.Dropdown(choices=['Malicious_comment','Economic_article'])
+iface = gr.Interface(fn=greet,title='Korean classification',description="한국어 악플 && 경제기사 긍부정 판별기",inputs=[intput,input2], outputs="text")
+iface.launch()

best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38a70d44ac05b9df19783bda115f68dcf35958b486fe31fbeeafb6ac135c6914
+size 498297451

best2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230bf534352b386cd67e21d46ae8a6460b11c1f15d8a6bcfb77668004eff4c68
+size 498300587

requirements.txt

@@ -0,0 +1,2 @@
+torch >= 1.8.0,!=1.12.0
+transformers >= 4.11.3