sonsus commited on
Commit
7058ef2
ยท
verified ยท
1 Parent(s): a3108f3

Update streamlit_app_local/app.py

Browse files
Files changed (1) hide show
  1. streamlit_app_local/app.py +6 -2
streamlit_app_local/app.py CHANGED
@@ -157,11 +157,15 @@ def main():
157
  st.title("โš”๏ธ VARCO ARENA โš”๏ธ")
158
  if st.session_state.korean:
159
  st.write(
160
- "**VARCO Arena๋Š” ๊ฐ ๋ชจ๋ธ์˜ ์ƒ์„ฑ๋œ ๊ฒฐ๊ณผ๋ฅผ ๋น„๊ต ํ‰๊ฐ€ํ•˜์—ฌ ๋ชจ๋ธ์˜ ์„ฑ๋Šฅ ์ˆœ์œ„๋ฅผ ์ œ๊ณตํ•˜๋Š” ์‹œ์Šคํ…œ์ž…๋‹ˆ๋‹ค. ๋ชจ๋ฒ”๋‹ต์•ˆ์„ ํ•„์š”๋กœ ํ•˜์ง€ ์•Š์œผ๋ฏ€๋กœ ์ปค์Šคํ…€ ํ…Œ์ŠคํŠธ์…‹ (50+ ํ–‰) ์„ ํ™œ์šฉํ•˜๋Š” ๊ฒฝ์šฐ ํŽธ๋ฆฌํ•œ ๋ฒค์น˜๋งˆํ‚น์ด ๊ฐ€๋Šฅํ•ฉ๋‹ˆ๋‹ค.**"
 
 
161
  )
162
  else:
163
  st.write(
164
- "**VARCO Arena is an LLM benchmarking system that compares model responses across customized test scenarios (recommend >50 prompts) without requiring reference answers.**"
 
 
165
  )
166
 
167
  st.divider()
 
157
  st.title("โš”๏ธ VARCO ARENA โš”๏ธ")
158
  if st.session_state.korean:
159
  st.write(
160
+ """**๋ฐ”๋ฅด์ฝ” ์•„๋ ˆ๋‚˜๋Š” ํ…Œ์ŠคํŠธ์…‹ ๋ช…๋ น์–ด๋ณ„๋กœ ๋น„๊ตํ•  ๋ชจ๋ธ(์ƒ์„ฑ๋ฌธ)์˜ ํ† ๋„ˆ๋จผํŠธ๋ฅผ ์ˆ˜ํ–‰ํ•˜๊ณ  ๊ฒฐ๊ณผ๋“ค์„ ์ข…ํ•ฉํ•˜์—ฌ ๋ชจ๋ธ๋“ค์˜ ์ˆœ์œ„๋ฅผ ๋งค๊ธฐ๋Š” ๋ฒค์น˜๋งˆํ‚น ์‹œ์Šคํ…œ์ž…๋‹ˆ๋‹ค. ์ด๊ฒƒ์€ reference ์•„์›ƒํ’‹๊ณผ ๋น„๊ตํ•˜์—ฌ ์Šน๋ฅ ์„ ๋งค๊ธฐ๋Š” ๋ฐฉ๋ฒ•๋ณด๋‹ค ์ •ํ™•ํ•˜๋ฉฐ ๋” ์ €๋ ดํ•ฉ๋‹ˆ๋‹ค.**
161
+
162
+ ๋ชจ๋ฒ”๋‹ต์•ˆ์„ ํ•„์š”๋กœ ํ•˜์ง€ ์•Š์œผ๋ฏ€๋กœ ์ปค์Šคํ…€ ํ…Œ์ŠคํŠธ์…‹ (50+ ํ–‰) ์„ ํ™œ์šฉํ•˜๋Š” ๊ฒฝ์šฐ ํŽธ๋ฆฌํ•œ ๋ฒค์น˜๋งˆํ‚น์ด ๊ฐ€๋Šฅํ•ฉ๋‹ˆ๋‹ค."""
163
  )
164
  else:
165
  st.write(
166
+ """**VARCO Arena is an LLM benchmarking system that compares model responses across customized test scenarios (recommend >50 prompts) without requiring reference answers.**
167
+
168
+ VARCO Arena conducts tournaments between models to be compared for each test set command, ranking models accurately at an affordable price. This is more accurate and cost-effective than rating win rates by comparing against reference outputs."""
169
  )
170
 
171
  st.divider()