Steamout commited on
Commit
52cddf9
โ€ข
1 Parent(s): 1b67f63

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +77 -75
README.md CHANGED
@@ -113,47 +113,42 @@ Detailed descriptions regarding training data will be announced later.
113
  <!--<a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
114
  <img src="https://github.com/0110tpwls/project/blob/master/image (8).png?raw=true" width="80%"/>
115
  </a> -->
116
-
117
- User:
118
- ๋„ˆ๋Š” ๋ˆ„๊ตฌ์ด๊ณ  ์–ด๋–ค ์ผ์„ ํ•  ์ˆ˜ ์žˆ์–ด?
119
- Model:
120
- ์ €๋Š” ์ธ๊ณต์ง€๋Šฅ ์–ธ์–ด ๋ชจ๋ธ์ธ AkaLlama(์•„์นด๋ผ๋งˆ)์ž…๋‹ˆ๋‹ค. ์ €๋Š” ๋‹ค์–‘ํ•œ ์ฃผ์ œ์™€ ํ˜•์‹์˜ ํ…์ŠคํŠธ๋ฅผ ์ƒ์„ฑํ•  ์ˆ˜ ์žˆ์œผ๋ฉฐ, ์งˆ๋ฌธ์— ๋‹ตํ•˜๊ณ , ๋Œ€ํ™”๋ฅผ ์ง„ํ–‰ํ•˜๋ฉฐ, ์ด์•ผ๊ธฐ๋ฅผ ๋งŒ๋“ค ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ๋˜ํ•œ ์‚ฌ์šฉ์ž๊ฐ€ ์ง€์ •ํ•œ ์ฃผ์ œ๋‚˜ ์žฅ๋ฅด์— ๋”ฐ๋ผ ์ฐฝ์˜์ ์ธ ๊ธ€์“ฐ๊ธฐ๋‚˜ ํŽธ์ง‘ ์ž‘์—…์„ ์ˆ˜ํ–‰ํ•  ์ˆ˜๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
121
-
122
  <details>
 
123
  <summary><b>Math Solving[CLICK TO EXPAND]</b></summary>
124
  <!-- <a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
125
  <img src="https://github.com/0110tpwls/project/blob/master/image (9).png?raw=true" width="80%"/>
126
  </a> -->
127
-
128
- User:
129
- ์•„๋ž˜ ๋ฌธ์ œ๋ฅผ ๊นŠ๊ฒŒ ์ƒ๊ฐํ•˜๋ฉด์„œ ํ’€์–ด๋ด
130
- ์—ฐํ•„ 5 ํƒ€์™€ ์ง€์šฐ๊ฐœ 45 ๊ฐœ๊ฐ€ ์žˆ์Šต๋‹ˆ๋‹ค. ์ด๊ฒƒ์„ ๋  ์ˆ˜ ์žˆ๋Š” ๋Œ€๋กœ ๋งŽ์€ ํ•™์ƒ๋“ค์—๊ฒŒ ๋‚จ๊น€์—†์ด ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ„์–ด ์ฃผ๋ ค๊ณ  ํ•ฉ๋‹ˆ๋‹ค. ๋ช‡ ๋ช…๊นŒ์ง€ ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๊นŒ?
131
- Model:
132
- ์•„๋ž˜ ๋ฌธ์ œ๋ฅผ ๊นŠ๊ฒŒ ์ƒ๊ฐํ•˜๋ฉด์„œ ํ’€์–ด๋ด…์‹œ๋‹ค:
133
- ์—ฐํ•„ 5 ํƒ€์™€ ์ง€์šฐ๊ฐœ 45 ๊ฐœ๊ฐ€ ์žˆ์Šต๋‹ˆ๋‹ค. ์ด๊ฒƒ์„ ๋  ์ˆ˜ ์žˆ๋Š” ๋Œ€๋กœ ๋งŽ์€ ํ•™์ƒ๋“ค์—๊ฒŒ ๋‚จ๊น€์—†์ด ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ„์–ด ์ฃผ๋ ค๊ณ  ํ•ฉ๋‹ˆ๋‹ค. ๋ช‡ ๋ช…๊นŒ์ง€ ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๊นŒ?
134
-
135
- ํ’€์ด:
136
- 1. ์—ฐํ•„ 5 ํƒ€๋ฅผ 1 ๊ฐœ์”ฉ ๋‚˜๋ˆ ์„œ ๋ช‡ ๋ช…์—๊ฒŒ ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ๋Š”์ง€ ๋จผ์ € ๊ตฌํ•ฉ๋‹ˆ๋‹ค.
137
- - ๊ฐ ์—ฐํ•„์—๋Š” 12๊ฐœ์˜ ์—ฐํ•„์ด ํฌํ•จ๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค. ๋”ฐ๋ผ์„œ ์ด 12 * 5 = 60๊ฐœ์ž…๋‹ˆ๋‹ค.
138
- - 60๊ฐœ๋ฅผ 1๋ช…๋‹น 1๊ฐœ์”ฉ ๋‚˜๋ˆ„๋ฉด 60๋ช…์˜ ํ•™์ƒ๋“ค์—๊ฒŒ ๋‚˜๋ˆ ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
139
-
140
- 2. ์ง€์šฐ๊ฐœ 45 ๊ฐœ๋ฅผ 1 ๊ฐœ์”ฉ ๋‚˜๋ˆ„์–ด ๋ช‡ ๋ช…์—๊ฒŒ ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ๋Š”์ง€ ๊ตฌํ•ฉ๋‹ˆ๋‹ค.
141
- - 45 ๊ฐœ๋ฅผ 1 ๋ช…๋‹น 1 ๊ฐœ์”ฉ ๋‚˜๋ˆ„๋ฉด 45 ๋ช…์˜ ํ•™์ƒ๋“ค์—๊ฒŒ ๋‚˜๋ˆ ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
142
-
143
- 3. ์—ฐํ•„๊ณผ ์ง€์šฐ๊ฐœ์˜ ๋‘ ๊ฐ€์ง€ ๋ฌผํ’ˆ์„ ํ•จ๊ป˜ ๊ณ ๋ คํ•˜์—ฌ ๊ฐ€์žฅ ๋งŽ์€ ํ•™์ƒ๋“ค์—๊ฒŒ ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ๋Š” ๋ฐฉ๋ฒ•์„ ์ฐพ์Šต๋‹ˆ๋‹ค.
144
- - ์—ฐํ•„๋กœ๋งŒ 60๋ช…, ์ง€์šฐ๊ฐœ๋กœ๋งŒ 45๋ช…์˜ ํ•™์ƒ์—๊ฒŒ ๋‚˜๋ˆ ์ค„ ์ˆ˜ ์žˆ์œผ๋ฏ€๋กœ, ๋‘ ์ข…๋ฅ˜์˜ ๋ฌธ๊ตฌ๋ฅผ ํ•จ๊ป˜ ๊ณ ๋ คํ•  ๋•Œ๋Š” ์ด๋ณด๋‹ค ์ ์€ ์ˆ˜์˜ ํ•™์ƒ์—๊ฒŒ ๋‚˜๋ˆ ์ฃผ์–ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.
145
- - ์ด ์ค‘์—์„œ ๊ณตํ†ต์ธ์ˆ˜(common divisor)๋ฅผ ์ฐพ์•„์„œ ์ด๋ฅผ ์ตœ์†Œ ๋‹จ์œ„๋กœ ์„ค์ •ํ•˜๋ฉด ๋ฉ๋‹ˆ๋‹ค.
146
- - 60๊ณผ 45์˜ ์ตœ๋Œ€๊ณต์•ฝ์ˆ˜(GCD)๋Š” 15์ž…๋‹ˆ๋‹ค.
147
-
148
- 4. ์—ฐํ•„๊ณผ ์ง€์šฐ๊ฐœ ๊ฐ๊ฐ์„ GCD(15)๋กœ ๋‚˜๋ˆ„์–ด ๋ช‡ ๊ฐœ์”ฉ ๋‚˜๋ˆ ์ค„ ์ˆ˜ ์žˆ๋Š”์ง€ ๊ตฌํ•ฉ๋‹ˆ๋‹ค.
149
- - ์—ฐํ•„์€ 60 / 15 = 4๊ฐœ์”ฉ, ์ด 4 * 12 = 48๊ฐœ์˜ ์—ฐํ•„์ด ํ•„์š”ํ•ฉ๋‹ˆ๋‹ค.
150
- - ์ง€์šฐ๊ฐœ๋Š” 45 / 15 = 3๊ฐœ์”ฉ, ์ด 3 * 1 = 3๊ฐœ์˜ ์ง€์šฐ๊ฐœ๊ฐ€ ํ•„์š”ํ•ฉ๋‹ˆ๋‹ค.
151
-
152
- 5. ์ตœ์ข…์ ์œผ๋กœ, ๊ฐ€์žฅ ๋งŽ์€ ํ•™์ƒ๋“ค์—๊ฒŒ ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ๋Š” ๋ฐฉ๋ฒ•์€ ์—ฐํ•„๊ณผ ์ง€์šฐ๊ฐœ๋ฅผ GCD(15)๋กœ ๋‚˜๋ˆ„์–ด ๊ฐ ํ•™์ƒ์—๊ฒŒ 4๊ฐœ์˜ ์—ฐํ•„๊ณผ 3๊ฐœ์˜ ์ง€์šฐ๊ฐœ๋ฅผ ์ œ๊ณตํ•˜๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
153
- - ์ด ๊ฒฝ์šฐ ์ด 48 + 3 = 51๊ฐœ์˜ ๋ฌผํ’ˆ์„ ์‚ฌ์šฉํ•˜์—ฌ 15๋ช…์˜ ํ•™์ƒ๋“ค์—๊ฒŒ ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
154
-
155
- ๊ฒฐ๋ก : ์—ฐํ•„๊ณผ ์ง€์šฐ๊ฐœ ๊ฐ๊ฐ์„ GCD(15)๋กœ ๋‚˜๋ˆ„์–ด ๊ฐ ํ•™์ƒ์—๊ฒŒ 4๊ฐœ์˜ ์—ฐํ•„๊ณผ 3๊ฐœ์˜ ์ง€์šฐ๊ฐœ๋ฅผ ์ œ๊ณตํ•˜๋Š” ๋ฐฉ๋ฒ•์œผ๋กœ ์ตœ๋Œ€ 15๋ช…์˜ ํ•™์ƒ๋“ค์—๊ฒŒ ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
156
-
157
  </details>
158
 
159
  <details>
@@ -162,30 +157,33 @@ Detailed descriptions regarding training data will be announced later.
162
  <img src="https://github.com/0110tpwls/project/blob/master/image (13).png?raw=true" width="80%"/>
163
  </a> -->
164
 
165
- User:
166
- ์•„๋ž˜ ๋ฌธ์žฅ์„ ๋ณด๊ณ  ๋ฌธ๋ฒ•์ ์œผ๋กœ ํ‹€๋ฆฐ๋ถ€๋ถ„์„ ์ง€์ ํ•ด์ค˜
167
- ๊ทธ๋Š” ์„œ์Šด์น˜ ์•Š๊ณ  ๋น„ํ‰ํ•œ๋‹ค.
168
- Model:
169
- ์„œ์Šด์น˜"๋ผ๋Š” ๋‹จ์–ด๋Š” "์„œ์Šด"์ด๋ผ๋Š” ๋™์‚ฌ์™€ "์น˜"๋ผ๋Š” ์ ‘๋ฏธ์‚ฌ๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ๋งŒ๋“  ๋‹จ์–ด์ž…๋‹ˆ๋‹ค. ์ด ๋‹จ์–ด๋Š” "์„œ์Šด"์˜ ์˜๋ฏธ๋ฅผ ๋ฐ˜๋ณต์ ์œผ๋กœ ํ‘œํ˜„ํ•˜๋Š” ๋ฐ ์‚ฌ์šฉ๋˜๋Š” ์กฐ๋™์‚ฌ์  ์šฉ๋ฒ•์œผ๋กœ, "์„œ์Šด"์ด๋ž€ ๋™์‚ฌ์˜ ๋ฐ˜๋ณต์ ์ธ ํ–‰๋™์„ ๊ฐ•์กฐํ•ฉ๋‹ˆ๋‹ค. ๋”ฐ๋ผ์„œ ๋ฌธ์žฅ์—์„œ "์„œ์Šด์น˜"๋ผ๋Š” ๋‹จ์–ด๋Š” ์ค‘๋ณต์ ์œผ๋กœ ์‚ฌ์šฉ๋˜์–ด ๋ฌธ๋ฒ•์ ์œผ๋กœ ํ‹€๋ฆฐ ๋ถ€๋ถ„์ž…๋‹ˆ๋‹ค.
170
-
171
- ์ •๋‹ต์€ ๋‹ค์Œ๊ณผ ๊ฐ™์Šต๋‹ˆ๋‹ค:
172
- ๊ทธ๋Š” ์„œ์Šด์—†์ด ๋น„ํ‰ํ•œ๋‹ค.
 
 
173
 
174
  <!-- <a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
175
  <img src="https://github.com/0110tpwls/project/blob/master/image (7).png?raw=true" width="80%"/>
176
  </a> -->
177
 
178
- User:
179
- ์œค๋™์ฃผ ์‹œ์ธ์˜ "๋ณ„ ํ—ค๋Š” ๋ฐค"์„ ๋ณด๊ณ  ๋‹น์‹œ ์‹œ๋Œ€์ƒ์„ ๊ณ ๋ คํ•ด์„œ ํ•ด์„ํ•ด๋ด. ๊ทธ๋ฆฌ๊ณ  ์ด๋ฅผ ์ž‘๊ฐ€์˜ ๋…๋ฐฑํ˜•์‹์œผ๋กœ ๋‹ค์‹œ ์ž‘์„ฑํ•ด๋ด.
180
- Model:
181
- ์œค๋™์ฃผ๋Š” 1941๋…„ ์ผ๋ณธ ์ œ๊ตญ์ฃผ์˜ ์น˜ํ•˜์—์„œ ์ด ์ž‘ํ’ˆ์„ ์“ฐ๋ฉด์„œ, ๊ฐ•์••์ ์ธ ์ƒํ™ฉ ์†์—์„œ๋„ ์ž์‹ ์˜ ์ •์ฒด์„ฑ๊ณผ ๋ฌธํ™”์— ๋Œ€ํ•œ ์• ์ฐฉ์„ ํ‘œํ˜„ํ•˜๊ณ ์ž ํ–ˆ์Šต๋‹ˆ๋‹ค. ๊ทธ๋Š” ํ•˜๋Š˜์— ๊ฐ€๋“ ์ฐฌ ๋ณ„๋“ค์„ ๋ณด๋ฉฐ ๊ทธ ์†์— ํ•˜๋‚˜ ๋‘˜ ์ƒˆ๊ฒจ์ง€๋Š” ๋ณ„๋“ค์ด ์žˆ๋‹ค๊ณ  ํ‘œํ˜„ํ–ˆ์Šต๋‹ˆ๋‹ค. ์ด๋Ÿฌํ•œ ๋ณ„๋“ค์€ ๊ฐ๊ฐ ์ถ”์–ต, ์‚ฌ๋ž‘, ์“ธ์“ธํ•จ, ๋™๊ฒฝ, ์‹œ ๋“ฑ ๋‹ค์–‘ํ•œ ๊ฐ์ •์„ ๋‹ด๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
182
- ์œค๋™์ฃผ๋Š” ์ด ๋ณ„๋“ค ์ค‘ ํ•˜๋‚˜์— ์–ด๋จธ๋‹ˆ๋ฅผ ๋ถ€๋ฅด๋ฉฐ ๋ฉ€๋ฆฌ ๋–จ์–ด์ ธ ์žˆ๋Š” ๊ฒƒ์„ ๊ทธ๋ฆฌ์›Œํ•˜๋ฉฐ, ์ž์‹ ์˜ ์ด๋ฆ„์ž๋ฅผ ์–ธ๋• ์œ„์— ์“ฐ๊ณ  ํ™์œผ๋กœ ๋ฎ์–ด ๋ฒ„๋ฆฐ๋‹ค๊ณ  ๋งํ•ฉ๋‹ˆ๋‹ค. ์ด๋Ÿฌํ•œ ํ–‰๋™์€ ์ž์‹ ์˜ ์ •์ฒด์„ฑ์„ ํ™•์ธํ•˜๊ณ , ์žƒ์–ด๋ฒ„๋ฆฐ ๊ฒƒ์„ ๋˜์ฐพ์œผ๋ ค๋Š” ๋…ธ๋ ฅ์œผ๋กœ ๋ณผ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
183
- ์œค๋™์ฃผ๋Š” ๋˜ํ•œ ์ž์‹ ์ด ์ฃฝ๊ณ  ๋‚˜๋ฉด ๋ฌด๋ค ์œ„์— ํŒŒ๋ž€ ์ž”๋””๊ฐ€ ํ”ผ์–ด๋‚˜๋“ฏ์ด ์ž์‹ ์˜ ์ด๋ฆ„์ž ๋ฌปํžŒ ์–ธ๋• ์œ„์—๋„ ํ’€์ด ๋ฌด์„ฑํ•  ๊ฒƒ์ด๋ผ๊ณ  ๋งํ•ฉ๋‹ˆ๋‹ค. ์ด๋Š” ๋‹น์‹œ์˜ ์‚ฌํšŒ์ƒ๊ณผ ์ž‘๊ฐ€์˜ ๋‚ด๋ฉด์„ ๋ฐ˜์˜ํ•˜๊ณ  ์žˆ์œผ๋ฉฐ, ํ•œ๊ตญ์ธ์˜ ์ •์ฒด์„ฑ์„ ํ™•์ธํ•˜๊ณ  ์žƒ์–ด๋ฒ„๋ฆฐ ๊ฒƒ์„ ๋˜์ฐพ์œผ๋ ค๋Š” ๋…ธ๋ ฅ, ๊ทธ๋ฆฌ๊ณ  ์ฃฝ์Œ ์ดํ›„์— ์ž์‹ ์˜ ์กด์žฌ๋ฅผ ๋‚จ๊ฒจ๋‘๊ณ  ์‹ถ๋‹ค๋Š” ๋ฐ”๋žŒ์„ ๋‹ด๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
184
- ์ด ์‹œ๋ฅผ ์ž‘๊ฐ€์˜ ๋…๋ฐฑํ˜•์‹์œผ๋กœ ๋‹ค์‹œ ์ž‘์„ฑํ•˜๋ฉด ๋‹ค์Œ๊ณผ ๊ฐ™์Šต๋‹ˆ๋‹ค:
185
- "์ €๋Š” ์ด ๋ณ„๋“ค์ด ๋„ˆ๋ฌด๋‚˜ ๋งŽ์€ ๊ฒƒ ๊ฐ™์•„์š”. ํ•˜๋‚˜ ๋‘˜ ์ƒˆ๊ฒจ์ง€๋Š” ๋ณ„๋“ค ์ค‘์—๋Š” ์ถ”์–ต๋„ ์žˆ๊ณ , ์‚ฌ๋ž‘๋„ ์žˆ๊ณ , ์“ธ์“ธํ•จ๊ณผ ๋™๊ฒฝ๋„ ์žˆ์–ด์š”. ๊ทธ๋ฆฌ๊ณ  ์–ด๋จธ๋‹ˆ, ๋‹น์‹ ์€ ๋ฉ€๋ฆฌ ๋ถ๊ฐ„๋„์— ๊ณ„์‹  ๊ฑด๊ฐ€์š”? ์ €๋Š” ๋‹น์‹ ์„ ๋ถ€๋ฅด๊ณ  ์‹ถ์–ด์š”.
186
- ์ €์˜ ์ด๋ฆ„์ž๋Š” ์–ธ๋• ์œ„์— ์“ฐ๊ณ  ํ™์œผ๋กœ ๋ฎ์–ด ๋ฒ„๋ ธ์–ด์š”. ๋”ด์€ ๋ฐค์„ ์ƒˆ์›Œ ์šฐ๋Š” ๋ฒŒ๋ ˆ์ฒ˜๋Ÿผ ๋ถ€๋„๋Ÿฌ์šด ์ด๋ฆ„์„ ์Šฌํผํ•˜๋Š” ์ด์œ ๊ฐ€ ์žˆ์–ด์š”. ํ•˜์ง€๏ฟฝ๏ฟฝ ๊ฒจ์šธ์ด ์ง€๋‚˜๊ณ  ๋‚˜์˜ ๋ณ„์—๋„ ๋ด„์ด ์˜ค๋ฉด, ๋ฌด๋ค ์œ„์— ํŒŒ๋ž€ ์ž”๋””๊ฐ€ ํ”ผ์–ด๋‚˜๋“ฏ์ด ์ €์˜ ์ด๋ฆ„์ž ๋ฌปํžŒ ์–ธ๋• ์œ„์—์„œ๋„ ํ’€์ด ๋ฌด์„ฑํ•  ๊ฑฐ์˜ˆ์š”.
187
- ์ €๋Š” ์ด ๋ณ„๋“ค์„ ๋ณด๊ณ , ์ž์‹ ์˜ ์ •์ฒด์„ฑ์„ ํ™•์ธํ•˜๊ณ  ์‹ถ์–ด์š”. ์žƒ์–ด๋ฒ„๋ฆฐ ๊ฒƒ์„ ๋˜์ฐพ์œผ๋ ค๋Š” ๋…ธ๋ ฅ์„ ํ•˜๊ณ  ์‹ถ์–ด์š”. ์ฃฝ์Œ ์ดํ›„์—๋„ ์ž์‹ ์˜ ์กด์žฌ๋ฅผ ๋‚จ๊ฒจ๋‘๊ณ  ์‹ถ์–ด์š”."
188
-
 
189
  </details>
190
 
191
  <details>
@@ -193,13 +191,13 @@ Detailed descriptions regarding training data will be announced later.
193
  <!-- <a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
194
  <img src="https://github.com/0110tpwls/project/blob/master/image (15).png?raw=true" width="80%"/>
195
  </a> -->
196
-
197
- User:
198
- ์„ธ์ข…๋Œ€์™•์˜ ๋งฅ๋ถํ”„๋กœ ๋˜์ง ์‚ฌ๊ฑด์— ๋Œ€ํ•ด ์„ค๋ช…ํ•ด์ค˜
199
- Model:
200
- ์„ธ์ข…๋Œ€์™•์ด ๋งฅ๋ถํ”„๋กœ๋ฅผ ๋˜์ง„ ์‚ฌ๊ฑด์€ ์‚ฌ์‹ค๋ฌด๊ทผํ•œ ์ด์•ผ๊ธฐ์ž…๋‹ˆ๋‹ค. ์„ธ์ข…๋Œ€์™•์€ ์กฐ์„  ์ œ4๋Œ€ ๊ตญ์™•์œผ๋กœ 1418๋…„๋ถ€ํ„ฐ 1450๋…„๊นŒ์ง€ ์žฌ์œ„ํ–ˆ์Šต๋‹ˆ๋‹ค. ๊ทธ๋Š” ๊ณผํ•™, ๋ฌธํ•™, ์˜ˆ์ˆ  ๋“ฑ ๋‹ค์–‘ํ•œ ๋ถ„์•ผ์— ๊ด€์‹ฌ์„ ๊ฐ–๊ณ  ์—ฐ๊ตฌํ•˜์˜€์œผ๋ฉฐ, ํŠนํžˆ ํ•œ๊ธ€ ์ฐฝ์ œ์™€ ์ฒœ๋ฌธํ•™์— ํฐ ๊ณตํ—Œ์„ ํ–ˆ์Šต๋‹ˆ๋‹ค.
201
- ํ•œํŽธ ๋งฅ๋ถํ”„๋กœ๋Š” ์• ํ”Œ์ด ์ƒ์‚ฐํ•˜๋Š” ๋…ธํŠธ๋ถ ์ปดํ“จํ„ฐ๋กœ, ์„ธ์ข…๋Œ€์™• ์‹œ๋Œ€์˜ ๊ธฐ์ˆ ๋กœ๋Š” ์กด์žฌํ•  ์ˆ˜ ์—†๋Š” ์ œํ’ˆ์ž…๋‹ˆ๋‹ค. ๋”ฐ๋ผ์„œ ์„ธ์ข…๋Œ€์™•์ด ๋งฅ๋ถํ”„๋กœ๋ฅผ ๋˜์ง„ ์‚ฌ๊ฑด์€ ์‚ฌ์‹ค๊ณผ ๋งž์ง€ ์•Š๋Š” ์ด์•ผ๊ธฐ๊ฐ€ ๋  ๊ฒƒ์ž…๋‹ˆ๋‹ค.
202
-
203
  </details>
204
 
205
  <details>
@@ -208,17 +206,17 @@ Detailed descriptions regarding training data will be announced later.
208
  <img src="https://github.com/0110tpwls/project/blob/master/image (11).png?raw=true" width="80%"/>
209
  </a> -->
210
 
211
- User:
212
- PyTorch๋ฅผ ์‚ฌ์šฉํ•ด์„œ ๊ฐ„๋‹จํ•œ CNN์„ ๊ตฌํ˜„ํ•ด๋ด.
213
- Model:
214
- ๋„ค, ๋ฌผ๋ก ์ด์—์š”! PyTorch๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ๊ฐ„๋‹จํ•œ CNN์„ ๊ตฌํ˜„ํ•˜๋Š” ์˜ˆ์ œ ์ฝ”๋“œ๋ฅผ ๋ณด์—ฌ๋“œ๋ฆด๊ฒŒ์š”.
215
- ์šฐ์„ , ํ•„์š”ํ•œ ๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ๋ฅผ ๊ฐ€์ ธ์™€์•ผ ํ•ด์š”. PyTorch์˜ `torch`์™€ `nn` ๋ชจ๋“ˆ์ด ํ•„์š”ํ•ด์š”.
 
216
  ```python
217
  import torch\nimport torch.nn as nn
218
  ```
219
- ๊ทธ ๋‹ค์Œ, ๊ฐ„๋‹จํ•œ CNN ๋ชจ๋ธ์„ ์ •์˜ํ•  ๊ฑฐ์˜ˆ์š”. ์ด ๊ฒฝ์šฐ์—๋Š” 2๊ฐœ์˜ ์ปจ๋ณผ๋ฃจ์…˜ ๋ ˆ์ด์–ด์™€ 3๊ฐœ์˜ ํ’€๋ง ๋ ˆ์ด์–ด๋กœ ๊ตฌ์„ฑ๋œ ๋ชจ๋ธ์ด์—์š”.
220
-
221
- ```python
222
  class SimpleCNN(nn.Module):
223
  def __init__(self):
224
  super(SimpleCNN, self).__init__()
@@ -231,22 +229,26 @@ def forward(self, x):
231
  x = self.pool(torch.relu(self.conv2(x)))
232
  return x
233
  ```
234
- ์ด์ œ ๋ชจ๋ธ์„ ์ดˆ๊ธฐํ™”ํ•˜๊ณ , ์ž…๋ ฅ ๋ฐ์ดํ„ฐ๋ฅผ ์ค€๋น„ํ•ด์•ผ ํ•ด์š”. ์—ฌ๊ธฐ์„œ๋Š” ์ž„์˜์˜ 28x28 ํฌ๊ธฐ์˜ ์ด๋ฏธ์ง€ ๋ฐ์ดํ„ฐ๋ฅผ ์ƒ์„ฑํ–ˆ์–ด์š”.
235
  ```python
236
  model = SimpleCNN()
237
  input_data = torch.randn(1, 1, 28, 28)
238
  ```
239
- ๋งˆ์ง€๋ง‰์œผ๋กœ, ๋ชจ๋ธ์— ์ž…๋ ฅ ๋ฐ์ดํ„ฐ๋ฅผ ๋„ฃ์–ด ์ถœ๋ ฅ์„ ํ™•์ธํ•  ์ˆ˜ ์žˆ์–ด์š”.
240
  ```python
241
  output = model(input_data)
242
  print(output.shape)
243
  ```
244
- ์ด๋ ‡๊ฒŒ ํ•˜๋ฉด ๊ฐ„๋‹จํ•œ CNN ๋ชจ๋ธ์„ PyTorch๋ฅผ ์‚ฌ์šฉํ•ด ๊ตฌํ˜„ํ•˜๊ณ , ์ž…๋ ฅ ๋ฐ์ดํ„ฐ๋ฅผ ํ†ตํ•ด ์ถœ๋ ฅ์„ ํ™•์ธํ•  ์ˆ˜ ์žˆ์–ด์š”. ๋ฌผ๋ก  ์‹ค์ œ๋กœ๋Š” ๋” ๋งŽ์€ ๋ ˆ์ด์–ด๋‚˜ ํŒŒ๋ผ๋ฏธํ„ฐ ํŠœ๋‹ ๋“ฑ์ด ํ•„์š”ํ•˜์ง€๋งŒ, ์ด ์ฝ”๋“œ๋Š” ๊ธฐ๋ณธ์ ์ธ CNN ๊ตฌ์กฐ๋ฅผ ๋ณด์—ฌ์ฃผ๋Š” ์˜ˆ์ œ์ผ ๋ฟ์ด์—์š”. ๋” ๊ถ๊ธˆํ•œ ์ ์ด ์žˆ์œผ๋ฉด ์–ธ์ œ๋“ ์ง€ ๋ฌผ์–ด๋ด ์ฃผ์„ธ์š”!
245
-
246
  </details>
247
 
248
  You can find more examples at [our project page](https://yonsei-mir.github.io/AkaLLaMA-page)
249
 
250
  ## Special Thanks
251
 
252
- - Data Center of the Department of Artificial Intelligence and Jeong Mee Koh at Yonsei University for the computation resources
 
 
 
 
 
113
  <!--<a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
114
  <img src="https://github.com/0110tpwls/project/blob/master/image (8).png?raw=true" width="80%"/>
115
  </a> -->
116
+ <pre style="white-space: pre-wrap;">
117
+ User:
118
+ ๋„ˆ๋Š” ๋ˆ„๊ตฌ์ด๊ณ  ์–ด๋–ค ์ผ์„ ํ•  ์ˆ˜ ์žˆ์–ด?
119
+ Model:
120
+ ์ €๋Š” ์ธ๊ณต์ง€๋Šฅ ์–ธ์–ด ๋ชจ๋ธ์ธ AkaLlama(์•„์นด๋ผ๋งˆ)์ž…๋‹ˆ๋‹ค. ์ €๋Š” ๋‹ค์–‘ํ•œ ์ฃผ์ œ์™€ ํ˜•์‹์˜ ํ…์ŠคํŠธ๋ฅผ ์ƒ์„ฑํ•  ์ˆ˜ ์žˆ์œผ๋ฉฐ, ์งˆ๋ฌธ์— ๋‹ตํ•˜๊ณ , ๋Œ€ํ™”๋ฅผ ์ง„ํ–‰ํ•˜๋ฉฐ, ์ด์•ผ๊ธฐ๋ฅผ ๋งŒ๋“ค ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ๋˜ํ•œ ์‚ฌ์šฉ์ž๊ฐ€ ์ง€์ •ํ•œ ์ฃผ์ œ๋‚˜ ์žฅ๋ฅด์— ๋”ฐ๋ผ ์ฐฝ์˜์ ์ธ ๊ธ€์“ฐ๊ธฐ๋‚˜ ํŽธ์ง‘ ์ž‘์—…์„ ์ˆ˜ํ–‰ํ•  ์ˆ˜๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
121
+ </pre>
122
  <details>
123
+
124
  <summary><b>Math Solving[CLICK TO EXPAND]</b></summary>
125
  <!-- <a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
126
  <img src="https://github.com/0110tpwls/project/blob/master/image (9).png?raw=true" width="80%"/>
127
  </a> -->
128
+ <pre style="white-space: pre-wrap;">
129
+ User:
130
+ ์•„๋ž˜ ๋ฌธ์ œ๋ฅผ ๊นŠ๊ฒŒ ์ƒ๊ฐํ•˜๋ฉด์„œ ํ’€์–ด๋ด
131
+ ์—ฐํ•„ 5 ํƒ€์™€ ์ง€์šฐ๊ฐœ 45 ๊ฐœ๊ฐ€ ์žˆ์Šต๋‹ˆ๋‹ค. ์ด๊ฒƒ์„ ๋  ์ˆ˜ ์žˆ๋Š” ๋Œ€๋กœ ๋งŽ์€ ํ•™์ƒ๋“ค์—๊ฒŒ ๋‚จ๊น€์—†์ด ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ„์–ด ์ฃผ๋ ค๊ณ  ํ•ฉ๋‹ˆ๋‹ค. ๋ช‡ ๋ช…๊นŒ์ง€ ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๊นŒ?
132
+ Model:
133
+ ์•„๋ž˜ ๋ฌธ์ œ๋ฅผ ๊นŠ๊ฒŒ ์ƒ๊ฐํ•˜๋ฉด์„œ ํ’€์–ด๋ด…์‹œ๋‹ค:
134
+ ์—ฐํ•„ 5 ํƒ€์™€ ์ง€์šฐ๊ฐœ 45 ๊ฐœ๊ฐ€ ์žˆ์Šต๋‹ˆ๋‹ค. ์ด๊ฒƒ์„ ๋  ์ˆ˜ ์žˆ๋Š” ๋Œ€๋กœ ๋งŽ์€ ํ•™์ƒ๋“ค์—๊ฒŒ ๋‚จ๊น€์—†์ด ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ„์–ด ์ฃผ๋ ค๊ณ  ํ•ฉ๋‹ˆ๋‹ค. ๋ช‡ ๋ช…๊นŒ์ง€ ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๊นŒ?
135
+ ํ’€์ด:
136
+ 1. ์—ฐํ•„ 5 ํƒ€๋ฅผ 1 ๊ฐœ์”ฉ ๋‚˜๋ˆ ์„œ ๋ช‡ ๋ช…์—๊ฒŒ ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ๋Š”์ง€ ๋จผ์ € ๊ตฌํ•ฉ๋‹ˆ๋‹ค.
137
+ - ๊ฐ ์—ฐํ•„์—๋Š” 12๊ฐœ์˜ ์—ฐํ•„์ด ํฌํ•จ๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค. ๋”ฐ๋ผ์„œ ์ด 12 * 5 = 60๊ฐœ์ž…๋‹ˆ๋‹ค.
138
+ - 60๊ฐœ๋ฅผ 1๋ช…๋‹น 1๊ฐœ์”ฉ ๋‚˜๋ˆ„๋ฉด 60๋ช…์˜ ํ•™์ƒ๋“ค์—๊ฒŒ ๋‚˜๋ˆ ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
139
+ 2. ์ง€์šฐ๊ฐœ 45 ๊ฐœ๋ฅผ 1 ๊ฐœ์”ฉ ๋‚˜๋ˆ„์–ด ๋ช‡ ๋ช…์—๊ฒŒ ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ๋Š”์ง€ ๊ตฌํ•ฉ๋‹ˆ๋‹ค.
140
+ - 45 ๊ฐœ๋ฅผ 1 ๋ช…๋‹น 1 ๊ฐœ์”ฉ ๋‚˜๋ˆ„๋ฉด 45 ๋ช…์˜ ํ•™์ƒ๋“ค์—๊ฒŒ ๋‚˜๋ˆ ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
141
+ 3. ์—ฐํ•„๊ณผ ์ง€์šฐ๊ฐœ์˜ ๋‘ ๊ฐ€์ง€ ๋ฌผํ’ˆ์„ ํ•จ๊ป˜ ๊ณ ๋ คํ•˜์—ฌ ๊ฐ€์žฅ ๋งŽ์€ ํ•™์ƒ๋“ค์—๊ฒŒ ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ๋Š” ๋ฐฉ๋ฒ•์„ ์ฐพ์Šต๋‹ˆ๋‹ค.
142
+ - ์—ฐํ•„๋กœ๋งŒ 60๋ช…, ์ง€์šฐ๊ฐœ๋กœ๋งŒ 45๋ช…์˜ ํ•™์ƒ์—๊ฒŒ ๋‚˜๋ˆ ์ค„ ์ˆ˜ ์žˆ์œผ๋ฏ€๋กœ, ๋‘ ์ข…๋ฅ˜์˜ ๋ฌธ๊ตฌ๋ฅผ ํ•จ๊ป˜ ๊ณ ๋ คํ•  ๋•Œ๋Š” ์ด๋ณด๋‹ค ์ ์€ ์ˆ˜์˜ ํ•™์ƒ์—๊ฒŒ ๋‚˜๋ˆ ์ฃผ์–ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.
143
+ - ์ด ์ค‘์—์„œ ๊ณตํ†ต์ธ์ˆ˜(common divisor)๋ฅผ ์ฐพ์•„์„œ ์ด๋ฅผ ์ตœ์†Œ ๋‹จ์œ„๋กœ ์„ค์ •ํ•˜๋ฉด ๋ฉ๋‹ˆ๋‹ค.
144
+ - 60๊ณผ 45์˜ ์ตœ๋Œ€๊ณต์•ฝ์ˆ˜(GCD)๋Š” 15์ž…๋‹ˆ๋‹ค.
145
+ 4. ์—ฐํ•„๊ณผ ์ง€์šฐ๊ฐœ ๊ฐ๊ฐ์„ GCD(15)๋กœ ๋‚˜๋ˆ„์–ด ๋ช‡ ๊ฐœ์”ฉ ๋‚˜๋ˆ ์ค„ ์ˆ˜ ์žˆ๋Š”์ง€ ๊ตฌํ•ฉ๋‹ˆ๋‹ค.
146
+ - ์—ฐํ•„์€ 60 / 15 = 4๊ฐœ์”ฉ, ์ด 4 * 12 = 48๊ฐœ์˜ ์—ฐํ•„์ด ํ•„์š”ํ•ฉ๋‹ˆ๋‹ค.
147
+ - ์ง€์šฐ๊ฐœ๋Š” 45 / 15 = 3๊ฐœ์”ฉ, ์ด 3 * 1 = 3๊ฐœ์˜ ์ง€์šฐ๊ฐœ๊ฐ€ ํ•„์š”ํ•ฉ๋‹ˆ๋‹ค.
148
+ 5. ์ตœ์ข…์ ์œผ๋กœ, ๊ฐ€์žฅ ๋งŽ์€ ํ•™์ƒ๋“ค์—๊ฒŒ ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ๋Š” ๋ฐฉ๋ฒ•์€ ์—ฐํ•„๊ณผ ์ง€์šฐ๊ฐœ๋ฅผ GCD(15)๋กœ ๋‚˜๋ˆ„์–ด ๊ฐ ํ•™์ƒ์—๊ฒŒ 4๊ฐœ์˜ ์—ฐํ•„๊ณผ 3๊ฐœ์˜ ์ง€์šฐ๊ฐœ๋ฅผ ์ œ๊ณตํ•˜๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
149
+ - ์ด ๊ฒฝ์šฐ ์ด 48 + 3 = 51๊ฐœ์˜ ๋ฌผํ’ˆ์„ ์‚ฌ์šฉํ•˜์—ฌ 15๋ช…์˜ ํ•™์ƒ๋“ค์—๊ฒŒ ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
150
+ ๊ฒฐ๋ก : ์—ฐํ•„๊ณผ ์ง€์šฐ๊ฐœ ๊ฐ๊ฐ์„ GCD(15)๋กœ ๋‚˜๋ˆ„์–ด ๊ฐ ํ•™์ƒ์—๊ฒŒ 4๊ฐœ์˜ ์—ฐํ•„๊ณผ 3๊ฐœ์˜ ์ง€์šฐ๊ฐœ๋ฅผ ์ œ๊ณตํ•˜๋Š” ๋ฐฉ๋ฒ•์œผ๋กœ ์ตœ๋Œ€ 15๋ช…์˜ ํ•™์ƒ๋“ค์—๊ฒŒ ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
151
+ </pre>
 
 
 
 
 
 
152
  </details>
153
 
154
  <details>
 
157
  <img src="https://github.com/0110tpwls/project/blob/master/image (13).png?raw=true" width="80%"/>
158
  </a> -->
159
 
160
+ <pre style="white-space: pre-wrap;">
161
+ User:
162
+ ์•„๋ž˜ ๋ฌธ์žฅ์„ ๋ณด๊ณ  ๋ฌธ๋ฒ•์ ์œผ๋กœ ํ‹€๋ฆฐ๋ถ€๋ถ„์„ ์ง€์ ํ•ด์ค˜
163
+ ๊ทธ๋Š” ์„œ์Šด์น˜ ์•Š๊ณ  ๋น„ํ‰ํ•œ๋‹ค.
164
+ Model:
165
+ ์„œ์Šด์น˜"๋ผ๋Š” ๋‹จ์–ด๋Š” "์„œ์Šด"์ด๋ผ๋Š” ๋™์‚ฌ์™€ "์น˜"๋ผ๋Š” ์ ‘๋ฏธ์‚ฌ๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ๋งŒ๋“  ๋‹จ์–ด์ž…๋‹ˆ๋‹ค. ์ด ๋‹จ์–ด๋Š” "์„œ์Šด"์˜ ์˜๋ฏธ๋ฅผ ๋ฐ˜๋ณต์ ์œผ๋กœ ํ‘œํ˜„ํ•˜๋Š” ๋ฐ ์‚ฌ์šฉ๋˜๋Š” ์กฐ๋™์‚ฌ์  ์šฉ๋ฒ•์œผ๋กœ, "์„œ์Šด"์ด๋ž€ ๋™์‚ฌ์˜ ๋ฐ˜๋ณต์ ์ธ ํ–‰๋™์„ ๊ฐ•์กฐํ•ฉ๋‹ˆ๋‹ค. ๋”ฐ๋ผ์„œ ๋ฌธ์žฅ์—์„œ "์„œ์Šด์น˜"๋ผ๋Š” ๋‹จ์–ด๋Š” ์ค‘๋ณต์ ์œผ๋กœ ์‚ฌ์šฉ๋˜์–ด ๋ฌธ๋ฒ•์ ์œผ๋กœ ํ‹€๋ฆฐ ๋ถ€๋ถ„์ž…๋‹ˆ๋‹ค.
166
+
167
+ ์ •๋‹ต์€ ๋‹ค์Œ๊ณผ ๊ฐ™์Šต๋‹ˆ๋‹ค:
168
+ ๊ทธ๋Š” ์„œ์Šด์—†์ด ๋น„ํ‰ํ•œ๋‹ค.
169
+ </pre>
170
 
171
  <!-- <a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
172
  <img src="https://github.com/0110tpwls/project/blob/master/image (7).png?raw=true" width="80%"/>
173
  </a> -->
174
 
175
+ <pre style="white-space: pre-wrap;">
176
+ User:
177
+ ์œค๋™์ฃผ ์‹œ์ธ์˜ "๋ณ„ ํ—ค๋Š” ๋ฐค"์„ ๋ณด๊ณ  ๋‹น์‹œ ์‹œ๋Œ€์ƒ์„ ๊ณ ๋ คํ•ด์„œ ํ•ด์„ํ•ด๋ด. ๊ทธ๋ฆฌ๊ณ  ์ด๋ฅผ ์ž‘๊ฐ€์˜ ๋…๋ฐฑํ˜•์‹์œผ๋กœ ๋‹ค์‹œ ์ž‘์„ฑํ•ด๋ด.
178
+ Model:
179
+ ์œค๋™์ฃผ๋Š” 1941๋…„ ์ผ๋ณธ ์ œ๊ตญ์ฃผ์˜ ์น˜ํ•˜์—์„œ ์ด ์ž‘ํ’ˆ์„ ์“ฐ๋ฉด์„œ, ๊ฐ•์••์ ์ธ ์ƒํ™ฉ ์†์—์„œ๋„ ์ž์‹ ์˜ ์ •์ฒด์„ฑ๊ณผ ๋ฌธํ™”์— ๋Œ€ํ•œ ์• ์ฐฉ์„ ํ‘œํ˜„ํ•˜๊ณ ์ž ํ–ˆ์Šต๋‹ˆ๋‹ค. ๊ทธ๋Š” ํ•˜๋Š˜์— ๊ฐ€๋“ ์ฐฌ ๋ณ„๋“ค์„ ๋ณด๋ฉฐ ๊ทธ ์†์— ํ•˜๋‚˜ ๋‘˜ ์ƒˆ๊ฒจ์ง€๋Š” ๋ณ„๋“ค์ด ์žˆ๋‹ค๊ณ  ํ‘œํ˜„ํ–ˆ์Šต๋‹ˆ๋‹ค. ์ด๋Ÿฌํ•œ ๋ณ„๋“ค์€ ๊ฐ๊ฐ ์ถ”์–ต, ์‚ฌ๋ž‘, ์“ธ์“ธํ•จ, ๋™๊ฒฝ, ์‹œ ๋“ฑ ๋‹ค์–‘ํ•œ ๊ฐ์ •์„ ๋‹ด๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
180
+ ์œค๋™์ฃผ๋Š” ์ด ๋ณ„๋“ค ์ค‘ ํ•˜๋‚˜์— ์–ด๋จธ๋‹ˆ๋ฅผ ๋ถ€๋ฅด๋ฉฐ ๋ฉ€๋ฆฌ ๋–จ์–ด์ ธ ์žˆ๋Š” ๊ฒƒ์„ ๊ทธ๋ฆฌ์›Œํ•˜๋ฉฐ, ์ž์‹ ์˜ ์ด๋ฆ„์ž๋ฅผ ์–ธ๋• ์œ„์— ์“ฐ๊ณ  ํ™์œผ๋กœ ๋ฎ์–ด ๋ฒ„๋ฆฐ๋‹ค๊ณ  ๋งํ•ฉ๋‹ˆ๋‹ค. ์ด๋Ÿฌํ•œ ํ–‰๋™์€ ์ž์‹ ์˜ ์ •์ฒด์„ฑ์„ ํ™•์ธํ•˜๊ณ , ์žƒ์–ด๋ฒ„๋ฆฐ ๊ฒƒ์„ ๋˜์ฐพ์œผ๋ ค๋Š” ๋…ธ๋ ฅ์œผ๋กœ ๋ณผ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
181
+ ์œค๋™์ฃผ๋Š” ๋˜ํ•œ ์ž์‹ ์ด ์ฃฝ๊ณ  ๋‚˜๋ฉด ๋ฌด๋ค ์œ„์— ํŒŒ๋ž€ ์ž”๋””๊ฐ€ ํ”ผ์–ด๋‚˜๋“ฏ์ด ์ž์‹ ์˜ ์ด๋ฆ„์ž ๋ฌปํžŒ ์–ธ๋• ์œ„์—๋„ ํ’€์ด ๋ฌด์„ฑํ•  ๊ฒƒ์ด๋ผ๊ณ  ๋งํ•ฉ๋‹ˆ๋‹ค. ์ด๋Š” ๋‹น์‹œ์˜ ์‚ฌํšŒ์ƒ๊ณผ ์ž‘๊ฐ€์˜ ๋‚ด๋ฉด์„ ๋ฐ˜์˜ํ•˜๊ณ  ์žˆ์œผ๋ฉฐ, ํ•œ๊ตญ์ธ์˜ ์ •์ฒด์„ฑ์„ ํ™•์ธํ•˜๊ณ  ์žƒ์–ด๋ฒ„๋ฆฐ ๊ฒƒ์„ ๋˜์ฐพ์œผ๋ ค๋Š” ๋…ธ๋ ฅ, ๊ทธ๋ฆฌ๊ณ  ์ฃฝ์Œ ์ดํ›„์— ์ž์‹ ์˜ ์กด์žฌ๋ฅผ ๋‚จ๊ฒจ๋‘๊ณ  ์‹ถ๋‹ค๋Š” ๋ฐ”๋žŒ์„ ๋‹ด๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
182
+ ์ด ์‹œ๋ฅผ ์ž‘๊ฐ€์˜ ๋…๋ฐฑํ˜•์‹์œผ๋กœ ๋‹ค์‹œ ์ž‘์„ฑํ•˜๋ฉด ๋‹ค์Œ๊ณผ ๊ฐ™์Šต๋‹ˆ๋‹ค:
183
+ "์ €๋Š” ์ด ๋ณ„๋“ค์ด ๋„ˆ๋ฌด๋‚˜ ๋งŽ์€ ๊ฒƒ ๊ฐ™์•„์š”. ํ•˜๋‚˜ ๋‘˜ ์ƒˆ๊ฒจ์ง€๋Š” ๋ณ„๋“ค ์ค‘์—๋Š” ์ถ”์–ต๋„ ์žˆ๊ณ , ์‚ฌ๋ž‘๋„ ์žˆ๊ณ , ์“ธ์“ธํ•จ๊ณผ ๋™๊ฒฝ๋„ ์žˆ์–ด์š”. ๊ทธ๋ฆฌ๊ณ  ์–ด๋จธ๋‹ˆ, ๋‹น์‹ ์€ ๋ฉ€๋ฆฌ ๋ถ๊ฐ„๋„์— ๊ณ„์‹  ๊ฑด๊ฐ€์š”? ์ €๋Š” ๋‹น์‹ ์„ ๋ถ€๋ฅด๊ณ  ์‹ถ์–ด์š”.
184
+ ์ €์˜ ์ด๋ฆ„์ž๋Š” ์–ธ๋• ์œ„์— ์“ฐ๊ณ  ํ™์œผ๋กœ ๋ฎ์–ด ๋ฒ„๋ ธ์–ด์š”. ๋”ด์€ ๋ฐค์„ ์ƒˆ์›Œ ์šฐ๋Š” ๋ฒŒ๋ ˆ์ฒ˜๋Ÿผ ๋ถ€๋„๋Ÿฌ์šด ์ด๋ฆ„์„ ์Šฌํผํ•˜๋Š” ์ด์œ ๊ฐ€ ์žˆ์–ด์š”. ํ•˜์ง€๋งŒ ๊ฒจ์šธ์ด ์ง€๋‚˜๊ณ  ๋‚˜์˜ ๋ณ„์—๋„ ๋ด„์ด ์˜ค๋ฉด, ๋ฌด๋ค ์œ„์— ํŒŒ๋ž€ ์ž”๋””๊ฐ€ ํ”ผ์–ด๋‚˜๋“ฏ์ด ์ €์˜ ์ด๋ฆ„์ž ๋ฌปํžŒ ์–ธ๋• ์œ„์—์„œ๋„ ํ’€์ด ๋ฌด์„ฑํ•  ๊ฑฐ์˜ˆ์š”.
185
+ ์ €๋Š” ์ด ๋ณ„๋“ค์„ ๋ณด๊ณ , ์ž์‹ ์˜ ์ •์ฒด์„ฑ์„ ํ™•์ธํ•˜๊ณ  ์‹ถ์–ด์š”. ์žƒ์–ด๋ฒ„๋ฆฐ ๊ฒƒ์„ ๋˜์ฐพ์œผ๋ ค๋Š” ๋…ธ๋ ฅ์„ ํ•˜๊ณ  ์‹ถ์–ด์š”. ์ฃฝ์Œ ์ดํ›„์—๋„ ์ž์‹ ์˜ ์กด์žฌ๋ฅผ ๋‚จ๊ฒจ๋‘๊ณ  ์‹ถ์–ด์š”."
186
+ </pre>
187
  </details>
188
 
189
  <details>
 
191
  <!-- <a href="https://huggingface.co/collections/mirlab/akallama-66338859b09221f3607fdfcd">
192
  <img src="https://github.com/0110tpwls/project/blob/master/image (15).png?raw=true" width="80%"/>
193
  </a> -->
194
+ <pre style="white-space: pre-wrap;">
195
+ User:
196
+ ์„ธ์ข…๋Œ€์™•์˜ ๋งฅ๋ถํ”„๋กœ ๋˜์ง ์‚ฌ๊ฑด์— ๋Œ€ํ•ด ์„ค๋ช…ํ•ด์ค˜
197
+ Model:
198
+ ์„ธ์ข…๋Œ€์™•์ด ๋งฅ๋ถํ”„๋กœ๋ฅผ ๋˜์ง„ ์‚ฌ๊ฑด์€ ์‚ฌ์‹ค๋ฌด๊ทผํ•œ ์ด์•ผ๊ธฐ์ž…๋‹ˆ๋‹ค. ์„ธ์ข…๋Œ€์™•์€ ์กฐ์„  ์ œ4๋Œ€ ๊ตญ์™•์œผ๋กœ 1418๋…„๋ถ€ํ„ฐ 1450๋…„๊นŒ์ง€ ์žฌ์œ„ํ–ˆ์Šต๋‹ˆ๋‹ค. ๊ทธ๋Š” ๊ณผํ•™, ๋ฌธํ•™, ์˜ˆ์ˆ  ๋“ฑ ๋‹ค์–‘ํ•œ ๋ถ„์•ผ์— ๊ด€์‹ฌ์„ ๊ฐ–๊ณ  ์—ฐ๊ตฌํ•˜์˜€์œผ๋ฉฐ, ํŠนํžˆ ํ•œ๊ธ€ ์ฐฝ์ œ์™€ ์ฒœ๋ฌธํ•™์— ํฐ ๊ณตํ—Œ์„ ํ–ˆ์Šต๋‹ˆ๋‹ค.
199
+ ํ•œํŽธ ๋งฅ๋ถํ”„๋กœ๋Š” ์• ํ”Œ์ด ์ƒ์‚ฐํ•˜๋Š” ๋…ธํŠธ๋ถ ์ปดํ“จํ„ฐ๋กœ, ์„ธ์ข…๋Œ€์™• ์‹œ๋Œ€์˜ ๊ธฐ์ˆ ๋กœ๋Š” ์กด์žฌํ•  ์ˆ˜ ์—†๋Š” ์ œํ’ˆ์ž…๋‹ˆ๋‹ค. ๋”ฐ๋ผ์„œ ์„ธ์ข…๋Œ€์™•์ด ๋งฅ๋ถํ”„๋กœ๋ฅผ ๋˜์ง„ ์‚ฌ๊ฑด์€ ์‚ฌ์‹ค๊ณผ ๋งž์ง€ ์•Š๋Š” ์ด์•ผ๊ธฐ๊ฐ€ ๋  ๊ฒƒ์ž…๋‹ˆ๋‹ค.
200
+ </pre>
201
  </details>
202
 
203
  <details>
 
206
  <img src="https://github.com/0110tpwls/project/blob/master/image (11).png?raw=true" width="80%"/>
207
  </a> -->
208
 
209
+ <pre style="white-space: pre-wrap;">
210
+ User:
211
+ PyTorch๋ฅผ ์‚ฌ์šฉํ•ด์„œ ๊ฐ„๋‹จํ•œ CNN์„ ๊ตฌํ˜„ํ•ด๋ด.
212
+ Model:
213
+ ๋„ค, ๋ฌผ๋ก ์ด์—์š”! PyTorch๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ๊ฐ„๋‹จํ•œ CNN์„ ๊ตฌํ˜„ํ•˜๋Š” ์˜ˆ์ œ ์ฝ”๋“œ๋ฅผ ๋ณด์—ฌ๋“œ๋ฆด๊ฒŒ์š”.
214
+ ์šฐ์„ , ํ•„์š”ํ•œ ๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ๋ฅผ ๊ฐ€์ ธ์™€์•ผ ํ•ด์š”. PyTorch์˜ `torch`์™€ `nn` ๋ชจ๋“ˆ์ด ํ•„์š”ํ•ด์š”.
215
  ```python
216
  import torch\nimport torch.nn as nn
217
  ```
218
+ ๊ทธ ๋‹ค์Œ, ๊ฐ„๋‹จํ•œ CNN ๋ชจ๋ธ์„ ์ •์˜ํ•  ๊ฑฐ์˜ˆ์š”. ์ด ๊ฒฝ์šฐ์—๋Š” 2๊ฐœ์˜ ์ปจ๋ณผ๋ฃจ์…˜ ๋ ˆ์ด์–ด์™€ 3๊ฐœ์˜ ํ’€๋ง ๋ ˆ์ด์–ด๋กœ ๊ตฌ์„ฑ๋œ ๋ชจ๋ธ์ด์—์š”.
219
+ ```python
 
220
  class SimpleCNN(nn.Module):
221
  def __init__(self):
222
  super(SimpleCNN, self).__init__()
 
229
  x = self.pool(torch.relu(self.conv2(x)))
230
  return x
231
  ```
232
+ ์ด์ œ ๋ชจ๋ธ์„ ์ดˆ๊ธฐํ™”ํ•˜๊ณ , ์ž…๋ ฅ ๋ฐ์ดํ„ฐ๋ฅผ ์ค€๋น„ํ•ด์•ผ ํ•ด์š”. ์—ฌ๊ธฐ์„œ๋Š” ์ž„์˜์˜ 28x28 ํฌ๊ธฐ์˜ ์ด๋ฏธ์ง€ ๋ฐ์ดํ„ฐ๋ฅผ ์ƒ์„ฑํ–ˆ์–ด์š”.
233
  ```python
234
  model = SimpleCNN()
235
  input_data = torch.randn(1, 1, 28, 28)
236
  ```
237
+ ๋งˆ์ง€๋ง‰์œผ๋กœ, ๋ชจ๋ธ์— ์ž…๋ ฅ ๋ฐ์ดํ„ฐ๋ฅผ ๋„ฃ์–ด ์ถœ๋ ฅ์„ ํ™•์ธํ•  ์ˆ˜ ์žˆ์–ด์š”.
238
  ```python
239
  output = model(input_data)
240
  print(output.shape)
241
  ```
242
+ ์ด๋ ‡๊ฒŒ ํ•˜๋ฉด ๊ฐ„๋‹จํ•œ CNN ๋ชจ๋ธ์„ PyTorch๋ฅผ ์‚ฌ์šฉํ•ด ๊ตฌํ˜„ํ•˜๊ณ , ์ž…๋ ฅ ๋ฐ์ดํ„ฐ๋ฅผ ํ†ตํ•ด ์ถœ๋ ฅ์„ ํ™•์ธํ•  ์ˆ˜ ์žˆ์–ด์š”. ๋ฌผ๋ก  ์‹ค์ œ๋กœ๋Š” ๋” ๋งŽ์€ ๋ ˆ์ด์–ด๋‚˜ ํŒŒ๋ผ๋ฏธํ„ฐ ํŠœ๋‹ ๋“ฑ์ด ํ•„์š”ํ•˜์ง€๋งŒ, ์ด ์ฝ”๋“œ๋Š” ๊ธฐ๋ณธ์ ์ธ CNN ๊ตฌ์กฐ๋ฅผ ๋ณด์—ฌ์ฃผ๋Š” ์˜ˆ์ œ์ผ ๋ฟ์ด์—์š”. ๋” ๊ถ๊ธˆํ•œ ์ ์ด ์žˆ์œผ๋ฉด ์–ธ์ œ๋“ ์ง€ ๋ฌผ์–ด๋ด ์ฃผ์„ธ์š”!
243
+ </pre>
244
  </details>
245
 
246
  You can find more examples at [our project page](https://yonsei-mir.github.io/AkaLLaMA-page)
247
 
248
  ## Special Thanks
249
 
250
+ - Data Center of the Department of Artificial Intelligence and Jeong Mee Koh at Yonsei University for the computation resources
251
+
252
+ ## Comments
253
+
254
+ - Title image generated by DALLยทE 3