Update README.md

README.md

@@ -10,14 +10,14 @@ Model Developers: Sogang University SGEconFinlab
 
 ### Model Description
 
-This model is a language model specialized in economics and finance. This was learned with various economic/finance-related data such as 한국은행 경제 용어, 금융용어사전, KDI시사용어사전, 회계,세무용어사전, 중소기업청전문용어사전, 한경경제용어사전, 맨큐경제학, TESAT 시사 용어 따라잡기, 맨큐경제학, 생글생글 한경, 오늘의 TESAT, 한경주니어 TESAT.
-The data source is listed below, and since the data was used for research/policy purposes, we do not wish to disclose the trained data. If you wish to use it, please contact the original author for permission to use it.
+This model is a language model specialized in economics and finance. This was learned with various economic/finance-related data.
+The data sources are listed below, and we are not releasing the data we trained on because it was used for research/policy purposes. 
+If you wish to use the original data rather than our training data, please contact the original author directly for permission to use it.
 
-- **Developed by:** Sogang University SGEconFinlab
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Base Model:** yanolja/KoSOLAR-10.7B-v0.2
+- **Developed by:** [Sogang University SGEconFinlab]
+- **Language(s) (NLP):** [Ko/En]
+- **License:** [apache-2.0]
+- **Base Model:** [yanolja/KoSOLAR-10.7B-v0.2]
 
 ### Model Sources [optional]
 
@@ -38,32 +38,62 @@ The data source is listed below, and since the data was used for research/policy
 [More Information Needed]
 
 
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
-
-[More Information Needed]
-
+peft_model_id = "SGEcon/KoSOLAR-10.7B-v0.2_fin_v4"
+config = PeftConfig.from_pretrained(peft_model_id)
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16
+)
+model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, quantization_config=bnb_config, device_map={"":0})
+model = PeftModel.from_pretrained(model, peft_model_id)
+tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
+model.eval()
+
+
+import re
+
+def gen(x):
+    inputs = tokenizer(f"### 질문: {x}\n\n### 답변:", return_tensors='pt', return_token_type_ids=False)
+    
+    # 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,
+        early_stopping=True,
+        num_return_sequences=4,  # 4개의 답변을 생성하도록 설정(답변 개수 설정 가능)
+        do_sample=True,
+        eos_token_id=tokenizer.eos_token_id,  # EOS 토큰 ID 사용
+        temperature=0.9,
+        top_p=0.8,
+        top_k=50
+    )
+    
+    complete_answers = []
+    for gen_seq in gened:
+        decoded = tokenizer.decode(gen_seq, skip_special_tokens=True).strip()
+
+        # "### 답변:" 문자열 이후의 텍스트만 추출
+        first_answer_start_idx = decoded.find("### 답변:") + len("### 답변:")
+        temp_answer = decoded[first_answer_start_idx:].strip()
+
+        # 두 번째 "### 답변:" 문자열 이전까지의 텍스트만 추출
+        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)
+    
+    return complete_answers
+
+    
 ## Training Details
 
 ### Training Data