Update README.md

README.md

@@ -1,6 +1,14 @@
 ---
 library_name: transformers
-license: apache-2.0
+license: cc-by-nc-4.0
+datasets:
+- kyujinpy/KOR-OpenOrca-Platypus-v3
+language:
+- ko
+- en
+tags:
+- Economic
+- Finance
 ---
 
 
@@ -37,42 +45,39 @@ If you wish to use the original data rather than our training data, please conta
 ## Conducting Conversation
 
     import re
+
     def gen(x):
         inputs = tokenizer(f"### 질문: {x}\n\n### 답변:", return_tensors='pt', return_token_type_ids=False)
     
-        # Move data to GPU (if available)
+        # 데이터를 GPU로 이동(사용 가능한 경우)
         inputs = {k: v.to(device="cuda" if torch.cuda.is_available() else "cpu") for k, v in inputs.items()}
 
         gened = model.generate(
             **inputs,
-            max_new_tokens=256,
+            max_new_tokens=256,  # 새로 생성할 토큰의 최대 개수
             early_stopping=True,
-            num_return_sequences=4,  
-            do_sample=True,
-            eos_token_id=tokenizer.eos_token_id,  
-            temperature=0.9,
-            top_p=0.8,
-            top_k=50
+            num_return_sequences=1,  # 하나의 답변만 생성
+            do_sample=True,  # 다양한 답변 생성을 위해 샘플링 활성화
+            eos_token_id=tokenizer.eos_token_id,  # EOS 토큰 ID 사용
+            temperature=0.9,  # 생성 다양성 조절을 위한 온도 설정
+            top_p=0.8,  # nucleus sampling에서 사용할 p 값
+            top_k=50  # top-k sampling에서 사용할 k 값
         )
     
-        complete_answers = []
-        for gen_seq in gened:
-            decoded = tokenizer.decode(gen_seq, skip_special_tokens=True).strip()
-
-            # Extract only the text after the string "### 답변:"
-            first_answer_start_idx = decoded.find("### 답변:") + len("### 답변:")
-            temp_answer = decoded[first_answer_start_idx:].strip()
-
-            # Extract only text up to the second "### 답변:" string
-            second_answer_start_idx = temp_answer.find("### 답변:")
-            if second_answer_start_idx != -1:
-                complete_answer = temp_answer[:second_answer_start_idx].strip()
-            else:
-                complete_answer = temp_answer  # 두 번째 "### 답변:"이 없는 경우 전체 답변 반환
-        
-            complete_answers.append(complete_answer)
+        # 생성된 시퀀스를 디코드하여 출력 텍스트로 변환
+        decoded = tokenizer.decode(gened[0], skip_special_tokens=True).strip()
+
+        # "### 답변:" 문자열 이후의 텍스트만 추출
+        answer_start_idx = decoded.find("### 답변:") + len("### 답변:")
+        complete_answer = decoded[answer_start_idx:].strip()
+
+        # 첫 번째 구두점(. ? !)을 찾아서 그 부분까지만 추출
+        match = re.search(r"[\.\?\!][^\.\?\!]*$", complete_answer)
+        if match:
+            complete_answer = complete_answer[:match.end()].strip()
     
-        return complete_answers
+        return complete_answer
+
 
 
     
@@ -133,4 +138,4 @@ If you wish to use the original data rather than our training data, please conta
 
 ## Citation [optional]
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->