sonsus commited on
Commit
a3108f3
โ€ข
1 Parent(s): 3313619

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +6 -2
app.py CHANGED
@@ -256,11 +256,15 @@ def main():
256
  st.title("โš”๏ธ VARCO ARENA โš”๏ธ")
257
  if st.session_state.korean:
258
  st.write(
259
- "**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.**"
 
 
260
  )
261
  else:
262
  st.write(
263
- "**VARCO Arena is an LLM benchmarking system that compares model responses across customized test scenarios (recommend >50 prompts) without requiring reference answers.**"
 
 
264
  )
265
 
266
  st.divider()
 
256
  st.title("โš”๏ธ VARCO ARENA โš”๏ธ")
257
  if st.session_state.korean:
258
  st.write(
259
+ """**๋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.**
260
+
261
+ ๋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."""
262
  )
263
  else:
264
  st.write(
265
+ """**VARCO Arena is an LLM benchmarking system that compares model responses across customized test scenarios (recommend >50 prompts) without requiring reference answers.**
266
+
267
+ 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."""
268
  )
269
 
270
  st.divider()