You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Exchange

The Exchange model is built on Metaโ€™s Llama 3.1 and developed using SFT (Supervised Fine-Tuning) and DPO (Direct Preference Optimization) techniques. It analyzes factors influencing exchange rates based on provided foreign exchange market data and generates reports predicting exchange rate movements. The model supports forecasts for major global currencies such as USD, JPY, and EUR, offering intuitive explanations that are easy to understand even for users without a financial background. A key differentiator of this system is its ability to provide insights into the uncertain future of foreign exchange trading, leveraging the capabilities of a large language model. Additionally, it effectively processes and analyzes complex financial data while integrating various unstructured data sources, enabling it to reflect real-time market changes for more accurate predictions.

Model Details

Usage Application Form

To use this model, please complete the application form and submit it via email [[email protected]]. Access will be granted after your application is reviewed and approved. We appreciate your cooperation and look forward to assisting you.

1. **Name:**
- (e.g., John Doe)
2. **Date of Birth:**
- (e.g., January 1, 1990)
3. **Affiliation:**
- Are you applying as a company or an individual? [ ] Company [ ] Individual
- Company Name (if applicable):
- Department (if applicable):
4. **Position/Role:**
- (e.g., Data Scientist, Researcher, etc.)
5. **Contact Information:**
- Email:
- Phone Number:
6. **Purpose of Use:**
- (e.g., Research and Development, Commercial use, Educational purposes, etc.)
7. **Detailed Reason for Use:**
- 1. Name and version of the model you wish to use:
- 2. Reason for selecting this model:
- 3. Objectives to achieve using this model:
- 4. Expected use cases (please describe in as much detail as possible):
8. **Data Security and Ethical Use Plan:**
- (Please describe your plans for data protection and ethical use.)

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("davidkim205/exchange")
model = AutoModelForCausalLM.from_pretrained(
    "davidkim205/exchange",
    device_map="auto",
    torch_dtype=torch.bfloat16,
)

text="""{์ฃผ์–ด์ง„ 2025-01-08 ์ˆ˜์š”์ผ๊นŒ์ง€์˜ ๊ฒฝ์ œ ์ง€ํ‘œ์™€ ๋‰ด์Šค์—์„œ, USD ํ™˜์œจ ๋ณ€๋™์— ์œ ์˜๋ฏธํ•œ ์„ ํ–‰ ์ง€ํ‘œ๋กœ ์ž‘์šฉํ•œ ์ •๋ณด๋ฅผ ์ฐพ์•„ ํŒจํ„ด์„ ๋ถ„์„ํ•˜๊ณ , ์ด ๊ณผ์ •์—์„œ ์–ป์€ ํ†ต์ฐฐ์„ ๋ฐœํœ˜ํ•˜์—ฌ 2025-01-09 ๋ชฉ์š”์ผ์˜ USD ํ™˜์œจ ๋ณ€๋™์„ ์˜ˆ์ธกํ•˜์—ฌ๋ผ.
๋ถ„์„ ๋ฐ ์˜ˆ์ธก ๊ฒฐ๊ณผ๋ฅผ ๊ธฐ๋ฐ˜์œผ๋กœ ์˜ˆ์ธก ์š”์•ฝ๋ฌธ์˜ ๋…ผ๋ฆฌ์  ์ผ๊ด€์„ฑ์„ ๊ฐ•ํ™”ํ•ด๋ผ.
๊ฒฐ๊ณผ๋Š” ์•„๋ž˜ ํ˜•์‹์— ๋งž์ถ”์–ด ์ž‘์„ฑํ•œ๋‹ค.

## ํ˜•์‹
### ๋ถ„์„
1. {๊ตฌ์ฒด์  ํ•ญ๋ชฉ}: {ํ•ญ๋ชฉ์— ๋Œ€ํ•œ ๊ฐ„๋‹จํ•œ ์„ค๋ช…}
...

### ์˜ˆ์ธก
{๋ถ„์„ ๋ฐ ์˜ˆ์ธก ๊ฒฐ๊ณผ๋ฅผ ํ•œ ๋ฌธ์žฅ์œผ๋กœ ์š”์•ฝ}
```csv
{์ •๋‹ต}
```

## USD ํ™˜์œจ
date,name,Open,High,Low,Close
2025-01-08,USD,1450.52,1463.49,1448.21,1462.0
2025-01-07,USD,1458.77,1465.07,1444.09,1450.52
2025-01-06,USD,1468.35,1474.36,1453.78,1458.77
2025-01-03,USD,1468.98,1473.9,1463.35,1469.76
2025-01-02,USD,1476.76,1476.76,1462.45,1468.98

## KOSPI ๋ฐ์ดํ„ฐ
date,name,Open,High,Low,Close,Volume
2025-01-08,KOSPI,2481.25,2526.77,2481.25,2526.1,326533
2025-01-07,KOSPI,2513.49,2521.86,2481.25,2481.25,373148


## S&P500 ๋ฐ์ดํ„ฐ
date,name,Open,High,Low,Close,Volume
2025-01-08,S&P500,5951.0,5959.55,5882.64,5887.82,1994316874
2025-01-07,S&P500,6012.66,6021.04,5942.8,5951.0,2045970603


## Gold ๋ฐ์ดํ„ฐ
date,name,Open,High,Low,Close,Volume
2025-01-08,Gold,2672.0,2683.9,2653.8,2677.1,150403
2025-01-07,Gold,2643.4,2678.5,2641.2,2672.0,132699


## Oil ๋ฐ์ดํ„ฐ
date,name,Open,High,Low,Close,Volume
2025-01-08,Oil,77.03,77.89,76.62,77.16,40416
2025-01-07,Oil,77.4,77.5,75.92,77.03,43538


## 2025-01-08 ๋‰ด์Šค
1. ๋ฏธ๊ตญ ๊ฒฝ์ œ ์ง€ํ‘œ๊ฐ€ ์•ˆ์ •์ ์ธ ๊ณ ์šฉ ์‹œ์žฅ๊ณผ ๊ฐ•ํ•œ ์„œ๋น„์Šค ๋ถ€๋ฌธ์„ ๋ณด์—ฌ์ฃผ๋ฉฐ ๋‹ฌ๋Ÿฌ ๊ฐ•์„ธ. 
2. ํ˜ธ์ฃผ ๋‹ฌ๋Ÿฌ๊ฐ€ ๋ฏธ๊ตญ ๋‹ฌ๋Ÿฌ์— ๋น„ํ•ด ์•ฝ์„ธ๋ฅผ ๋ณด์˜€์œผ๋‚˜ ๊ธˆ๋ฆฌ์— ํฐ ์˜ํ–ฅ์€ ์—†์„ ๊ฒƒ์œผ๋กœ ์ „๋ง. 
3. ๋ฏธ๊ตญ ๋‹ฌ๋Ÿฌ ๊ฐ€์น˜๊ฐ€ 2.8395 ๋ผ๋ฆฌ๋ฅผ ๊ธฐ๋กํ•˜๋ฉฐ ์กฐ์ง€์•„ ํ™˜์œจ ์ƒ์Šน.  

## 2025-01-07 ๋‰ด์Šค
- **์ค‘๊ตญ ์œ„์•ˆํ™” ํ™˜์œจ ๋ฐฉ์–ด:** ์ค‘๊ตญ ์ค‘์•™์€ํ–‰์€ 2025๋…„์— ์œ„์•ˆํ™” ๊ฐ€์น˜ ํ•˜๋ฝ์„ ๋ฐฉ์ง€ํ•˜๊ธฐ ์œ„ํ•ด ๊ฐ•๋ ฅํžˆ ๋Œ€์ฒ˜ํ•  ์˜ˆ์ •.  
- **์œ ๋กœ-๋‹ฌ๋Ÿฌ ํŒจ๋ฆฌํ‹ฐ:** ์œ ๋กœํ™”์™€ ๋ฏธ๊ตญ ๋‹ฌ๋Ÿฌ์˜ ๊ฐ€์น˜๊ฐ€ ๋™์ผํ–ˆ๋˜ ๋งˆ์ง€๋ง‰ ์‹œ๊ธฐ๋Š” 2022๋…„, ํ˜„์žฌ ๋‹ค์‹œ ํŒจ๋ฆฌํ‹ฐ ๊ฐ€๋Šฅ์„ฑ ์–ธ๊ธ‰.  
 
## 2025-01-06 ๋‰ด์Šค
- ๋ฏธ๊ตญ ๋‹ฌ๋Ÿฌ์˜ ๊ตญ์ œ ์ค€๋น„ ํ†ตํ™”๋กœ์„œ์˜ ๋น„์ค‘์ด 30๋…„ ๋งŒ์— ์ตœ์ €์น˜๋ฅผ ๊ธฐ๋กํ•˜๋ฉฐ, ์ค‘์•™์€ํ–‰๋“ค์ด ๋‹ค๋ฅธ ํ†ตํ™”์™€ ๊ธˆ์— ์ง‘์ค‘ํ•˜๊ณ  ์žˆ์Œ. ํ˜„์žฌ ์ถ”์„ธ๋Œ€๋กœ๋ผ๋ฉด 2034๋…„๊นŒ์ง€ ๋‹ฌ๋Ÿฌ ๋น„์ค‘์ด 50% ์ดํ•˜๋กœ ๋–จ์–ด์งˆ ๊ฐ€๋Šฅ์„ฑ์ด ์žˆ์Œ.  
1. **ํŒœ์œ  ๊ฐ€๊ฒฉ ์ƒ์Šน**: ๋ง๋ ˆ์ด์‹œ์•„ ํŒœ์œ ๋Š” ์ˆ˜์š” ์ฆ๊ฐ€์™€ ์œ ๋ฆฌํ•œ ํ™˜์œจ๋กœ ์ธํ•ด ์ƒ์Šน.  
12. **๋Œ€๋‘ ์„ ๋ฌผ ๊ฐœ์š”**: ๋Œ€๋‘ ์„ ๋ฌผ์€ ๊ฐ€๊ฒฉ ๋ณ€๋™์„ ์˜ˆ์ธกํ•˜๊ฑฐ๋‚˜ ํ—ค์ง•ํ•˜๊ธฐ ์œ„ํ•œ ์œ ๋™์„ฑ ๋†’์€ ๋„๊ตฌ. }"""

messages = [
    {"role": "user", "content": text},
]
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=256)
print(tokenizer.decode(outputs[0]))
### ๋ถ„์„

1. **๋‹ฌ๋Ÿฌ ๊ฐ•์„ธ ์œ ์ง€**: ๋ฏธ๊ตญ์˜ ๊ฒฝ์ œ ์ง€ํ‘œ๊ฐ€ ๊ฐ•์„ธ๋ฅผ ์œ ์ง€ํ•˜๊ณ  ์žˆ์œผ๋ฉฐ, ์„œ๋น„์Šค์—… ๋ฐ ๊ณ ์šฉ ์ง€ํ‘œ๋Š” ํŠนํžˆ ๊ธ์ •์ ์ธ ์˜ํ–ฅ์„ ๋ฏธ์ณค์Šต๋‹ˆ๋‹ค. ์ด๋Š” ๋‹ฌ๋Ÿฌ ๊ฐ•์„ธ๋ฅผ ๋’ท๋ฐ›์นจํ•˜๋Š” ์ฃผ์š” ์š”์ธ์ž…๋‹ˆ๋‹ค. ๋˜ํ•œ, ๊ธ€๋กœ๋ฒŒ ์ฃผ์š” ํ†ตํ™” ๋Œ€๋น„ ๋‹ฌ๋Ÿฌ์˜ ์ƒ๋Œ€์  ๊ฐ•์„ธ๊ฐ€ ์ง€์†๋˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.

2. **๊ตญ๋‚ด์™ธ ๊ฒฝ์ œ ๋ถˆํ™•์‹ค์„ฑ ํ™•๋Œ€**: ํ•œ๊ตญ ์ •์น˜์  ๋ถˆ์•ˆ๊ณผ ๊ตญ์ œ์  ํŠธ๋Ÿผํ”„ ๊ด€์„ธ ์ •์ฑ… ๋ณ€ํ™” ๋“ฑ์ด ์›ํ™” ์•ฝ์„ธ๋ฅผ ์‹ฌํ™”์‹œํ‚ค๊ณ  ์žˆ์œผ๋ฉฐ, ์ด๋Š” ํ™˜์œจ ์ƒ์Šน ์••๋ ฅ์œผ๋กœ ์ž‘์šฉํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. ํ•œํŽธ, ๋ฏธ๊ตญ ๊ฒฝ์ œ์˜ ์ƒ๋Œ€์  ์•ˆ์ •์„ฑ๊ณผ ์„ฑ์žฅ ๊ธฐ๋Œ€๊ฐ์ด ๋‹ฌ๋Ÿฌ ๊ฐ€์น˜์— ์ถ”๊ฐ€์ ์ธ ์ƒ์Šน๋ ฅ์„ ๋ถ€์—ฌํ•ฉ๋‹ˆ๋‹ค.

3. **์™ธ๊ตญ์ธ ํˆฌ์ž ์ฆ๊ฐ€ ๋ฐ ์ฝ”์Šคํ”ผ ์ƒ์Šน**: ์™ธ๊ตญ์ธ๊ณผ ๊ธฐ๊ด€์˜ ๋งค์ˆ˜์„ธ๊ฐ€ ์ฆ๊ฐ€ํ•˜๋ฉด์„œ ์ฝ”์Šคํ”ผ๋Š” ์•ˆ์ •์ ์ธ ์ƒ์Šน์„ธ๋ฅผ ์œ ์ง€ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. ์ด๋Š” ํ™˜์œจ ํ•˜๋ฝ ์••๋ ฅ์œผ๋กœ ์ž‘์šฉํ•  ๊ฐ€๋Šฅ์„ฑ์ด ์žˆ์Šต๋‹ˆ๋‹ค.
 
4. **์›์œ ์™€ ๊ธˆ ๊ฐ€๊ฒฉ ์ƒ์Šน**: ๊ตญ์ œ ์›์œ ์™€ ๊ธˆ ๊ฐ€๊ฒฉ์ด ์ƒ์Šน์„ธ๋ฅผ ๋ณด์ด๋ฉฐ ์•ˆ์ „ ์ž์‚ฐ์œผ๋กœ์„œ์˜ ํˆฌ์ž์ž ์‹ ๋ขฐ๋„๋ฅผ ํ™•๋Œ€ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. ์ด๋Š” ๊ธ€๋กœ๋ฒŒ ๊ฒฝ์ œ ๋ถˆํ™•์‹ค์„ฑ์ด ๋†’์•„์ง์— ๋”ฐ๋ผ ์•ˆ์ „ ์ž์‚ฐ ์„ ํ˜ธ๊ฐ€ ๊ฐ•ํ™”๋œ ์š”์ธ์œผ๋กœ ํ•ด์„๋ฉ๋‹ˆ๋‹ค.
### ์˜ˆ์ธก

2025๋…„ 1์›” 9์ผ USD ํ™˜์œจ์€ ๋ฏธ๊ตญ ๊ฒฝ์ œ์˜ ๊ฐ•ํ•œ ์ง€ํ‘œ์™€ ๋‹ฌ๋Ÿฌ ๊ฐ•์„ธ ํ๋ฆ„, ๊ทธ๋ฆฌ๊ณ  ๊ตญ๋‚ด์™ธ ๋ถˆํ™•์‹ค์„ฑ์ด ์ƒ์กดํ•˜๋Š” ๊ฐ€์šด๋ฐ, ๋ณ€๋™์„ฑ์ด ์œ ์ง€๋  ๊ฐ€๋Šฅ์„ฑ์ด ์žˆ์Šต๋‹ˆ๋‹ค. ๋‹ค๋งŒ, ์™ธ๊ตญ์ธ๊ณผ ๊ธฐ๊ด€ ํˆฌ์ž์ž๋“ค์˜ ๋งค์ˆ˜์„ธ์™€ ๊ตญ๋‚ด ํ™˜ํ—ค์ง€ ์›€์ง์ž„์ด ํ™˜์œจ ํ•˜๋ฝ ์š”์ธ์„ ์ œ๊ณตํ•  ๊ฒƒ์ž…๋‹ˆ๋‹ค. ์ด์— ๋”ฐ๋ผ, USD/์› ํ™˜์œจ์€ ์ „์ผ ์ข…๊ฐ€(1462) ๋Œ€๋น„ ์†Œํญ ํ•˜๋ฝ์„ธ๋ฅผ ๋ณด์ด๋ฉฐ, ์ข…๊ฐ€๊ฐ€ **1453.21์›**์— ๋งˆ๊ฐํ•  ๊ฒƒ์œผ๋กœ ์˜ˆ์ธก๋ฉ๋‹ˆ๋‹ค.

```csv
date,Open,High,Low,Close
2025-01-09,1462.0,1463.51,1450.3,1453.21
```

Evaluation

Ranking

Ranking refers to the process of listing multiple values to assess their relative magnitude. During January 2025, the accuracy of the High and Low values predicted by other banks and Exchange for USD exchange rates was calculated to determine rankings. The accuracy for High and Low values was determined by calculating the average MAPE (Mean Absolute Percentage Error) for each and using it to rank the predictions. MAPE calculates the average error between the predicted and actual exchange rates as a percentage, where a lower value indicates higher prediction accuracy.

USD Currency

The Rank column represents the accuracy ranking of each Site based on MAPE values. The Site column lists the names of various banking sites providing exchange rate predictions. The Time column indicates the prediction period, specifying the timeframe for which the exchange rate was forecasted. The USD MAPE(high, low) column represents the average MAPE for USD predictions over January 2025, calculated as the mean of the MAPE for High and Low values.

Rank Site Time USD MAPE(high,low)
1 KEB Hana Bank 09-26 0.24
2 Korea Trade Insurance Corp. 09-26 0.25
3 Shinhan Bank 09-26 0.27
3 Woori Bank 09-26 0.27
5 KOOKMIN BANK 09-26 0.30
5 iM Bank 09-26 0.30
7 Exchange 00-24 0.32

Global Currency

Among existing banks, only one provides exchange rate predictions for global currencies against KRW, while most banks either do not offer predictions for global currencies or only provide USD-based exchange rate predictions. Therefore, to evaluate the USD-based exchange rate predictions, the following formula was used to convert the previous day's closing price into KRW-based exchange rates and collect the predicted values.

EUR/USD => 1 EUR per USD (prediction unit provided by the bank)  
USD/JPY => 1 USD per JPY (prediction unit provided by the bank)  
USD/KRW => Previous day's closing price (actual exchange rate)

1. (USD / EUR) * (KRW / USD) = KRW / EUR = (1 EUR per KRW)  
2. (KRW / USD) / (JPY / USD) = KRW / JPY = (1 JPY per KRW)

The Rank column represents the accuracy ranking of each Site based on MAPE values. The Site column lists the names of various banking sites providing exchange rate predictions. The Time column indicates the prediction period, specifying the timeframe for which the exchange rate was forecasted. The EUR MAPE(high, low) column represents the average MAPE for EUR predictions over January 2025, calculated as the mean of the MAPE for High and Low values. The JPY MAPE(high, low) column represents the average MAPE for JPY predictions over January 2025, calculated as the mean of the MAPE for High and Low values.

Rank Site Time EUR MAPE(high,low) JPY MAPE(high,low)
1 Exchange 00-24 0.22 0.43
2 iM Bank 09-26 0.36 0.52
3 KOOKMIN BANK 09-26 0.33 0.58
4 KEB Hana Bank 09-26 0.45 0.61
5 Shinhan Bank 09-26 0.52 0.63
- Woori Bank - Not provided Not provided
- Korea Trade Insurance Corp. - Not provided Not provided
Downloads last month
21
Safetensors
Model size
8.03B params
Tensor type
BF16
ยท
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Collection including davidkim205/exchange