Update README.md

README.md

@@ -14,18 +14,10 @@ This model is a language model specialized in economics and finance. This was le
 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]
-- **Language(s) (NLP):** [Ko/En]
-- **License:** [apache-2.0]
-- **Base Model:** [yanolja/KoSOLAR-10.7B-v0.2]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Developed by:** Sogang University SGEconFinlab
+- **Language(s) (NLP):** Ko/En
+- **License:** apache-2.0
+- **Base Model:** yanolja/KoSOLAR-10.7B-v0.2
 
 ## Uses
 
@@ -41,57 +33,57 @@ If you wish to use the original data rather than our training data, please conta
 ## How to Get Started with the Model
 
 
-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()
+    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)
+    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
-    )
+        # Move data to GPU (if available)
+        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,  
+            do_sample=True,
+            eos_token_id=tokenizer.eos_token_id,  
+            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 = []
+        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)
+            complete_answers.append(complete_answer)
     
-    return complete_answers
+        return complete_answers
 
     
 ## Training Details
@@ -152,43 +144,6 @@ def gen(x):
 #### Summary
 
 
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
 ## 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. -->