jujbob commited on
Commit
80bc6c9
โ€ข
1 Parent(s): caa8569

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -10,7 +10,7 @@ tags:
10
  base_model:
11
  - meta-llama/Meta-Llama-3-8B
12
  - jeiku/Average_Test_v1
13
- - ResplendentAI/RP_Format_QuoteAsterisk_Llama3
14
  ---
15
 
16
 
@@ -31,7 +31,7 @@ base_model:
31
  - ํ•œ๊ตญ์–ด ๋ฌธํ™”, ์–ธ์–ด๋ฅผ ๊ณ ๋ คํ•ด ์–ธ์–ดํ•™์ž๊ฐ€ ์ œ์ž‘ํ•œ ๋ฐ์ดํ„ฐ๋ฅผ ํ™œ์šฉํ•œ ๋ฏธ์„ธ์กฐ์ •
32
  - ๊ฐ•ํ™”ํ•™์Šต
33
  ์ด ๋ชจ๋“ ๊ฒŒ ํ•œ๊บผ๋ฒˆ์— ์ ์šฉ๋˜๊ณ  ์ƒ์—…์  ์ด์šฉ์ด ๊ฐ€๋Šฅํ•œ Bllossom์„ ์ด์šฉํ•ด ์—ฌ๋Ÿฌ๋ถ„ ๋งŒ์˜ ๋ชจ๋ธ์„ ๋งŒ๋“ค์–ด๋ณด์„ธ์šฅ!
34
- ๋ณธ ๋ชจ๋ธ์€ 4GB GPU์—์„œ ๊ตฌ๋™ ๊ฐ€๋Šฅํ•œ ์–‘์žํ™” ๋ชจ๋ธ์ž…๋‹ˆ๋‹ค!
35
 
36
  1. Bllossom-8B๋Š” ์„œ์šธ๊ณผ๊ธฐ๋Œ€, ํ…Œ๋””์ธ, ์—ฐ์„ธ๋Œ€ ์–ธ์–ด์ž์› ์—ฐ๊ตฌ์‹ค์˜ ์–ธ์–ดํ•™์ž์™€ ํ˜‘์—…ํ•ด ๋งŒ๋“  ์‹ค์šฉ์ฃผ์˜๊ธฐ๋ฐ˜ ์–ธ์–ด๋ชจ๋ธ์ž…๋‹ˆ๋‹ค! ์•ž์œผ๋กœ ์ง€์†์ ์ธ ์—…๋ฐ์ดํŠธ๋ฅผ ํ†ตํ•ด ๊ด€๋ฆฌํ•˜๊ฒ ์Šต๋‹ˆ๋‹ค ๋งŽ์ด ํ™œ์šฉํ•ด์ฃผ์„ธ์š” ๐Ÿ™‚
37
  2. ์ดˆ ๊ฐ•๋ ฅํ•œ Advanced-Bllossom 8B, 70B๋ชจ๋ธ, ์‹œ๊ฐ-์–ธ์–ด๋ชจ๋ธ์„ ๋ณด์œ ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค! (๊ถ๊ธˆํ•˜์‹ ๋ถ„์€ ๊ฐœ๋ณ„ ์—ฐ๋ฝ์ฃผ์„ธ์š”!!)
@@ -98,19 +98,19 @@ Invoke the llama.cpp server or the CLI.
98
  CLI:
99
 
100
  ```bash
101
- llama-cli --hf-repo jeiku/SOVL_Llama3_8B-Q4_K_M-GGUF --model sovl_llama3_8b.Q4_K_M.gguf -p "The meaning to life and the universe is"
102
  ```
103
 
104
  Server:
105
 
106
  ```bash
107
- llama-server --hf-repo jeiku/SOVL_Llama3_8B-Q4_K_M-GGUF --model sovl_llama3_8b.Q4_K_M.gguf -c 2048
108
  ```
109
 
110
  Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
111
 
112
  ```
113
- git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m sovl_llama3_8b.Q4_K_M.gguf -n 128
114
  ```
115
 
116
 
 
10
  base_model:
11
  - meta-llama/Meta-Llama-3-8B
12
  - jeiku/Average_Test_v1
13
+ - MLP-KTLim/llama-3-Korean-Bllossom-8B
14
  ---
15
 
16
 
 
31
  - ํ•œ๊ตญ์–ด ๋ฌธํ™”, ์–ธ์–ด๋ฅผ ๊ณ ๋ คํ•ด ์–ธ์–ดํ•™์ž๊ฐ€ ์ œ์ž‘ํ•œ ๋ฐ์ดํ„ฐ๋ฅผ ํ™œ์šฉํ•œ ๋ฏธ์„ธ์กฐ์ •
32
  - ๊ฐ•ํ™”ํ•™์Šต
33
  ์ด ๋ชจ๋“ ๊ฒŒ ํ•œ๊บผ๋ฒˆ์— ์ ์šฉ๋˜๊ณ  ์ƒ์—…์  ์ด์šฉ์ด ๊ฐ€๋Šฅํ•œ Bllossom์„ ์ด์šฉํ•ด ์—ฌ๋Ÿฌ๋ถ„ ๋งŒ์˜ ๋ชจ๋ธ์„ ๋งŒ๋“ค์–ด๋ณด์„ธ์šฅ!
34
+ ๋ณธ ๋ชจ๋ธ์€ 42GB GPU์—์„œ ๊ตฌ๋™ ๊ฐ€๋Šฅํ•œ ์–‘์žํ™” ๋ชจ๋ธ์ž…๋‹ˆ๋‹ค!
35
 
36
  1. Bllossom-8B๋Š” ์„œ์šธ๊ณผ๊ธฐ๋Œ€, ํ…Œ๋””์ธ, ์—ฐ์„ธ๋Œ€ ์–ธ์–ด์ž์› ์—ฐ๊ตฌ์‹ค์˜ ์–ธ์–ดํ•™์ž์™€ ํ˜‘์—…ํ•ด ๋งŒ๋“  ์‹ค์šฉ์ฃผ์˜๊ธฐ๋ฐ˜ ์–ธ์–ด๋ชจ๋ธ์ž…๋‹ˆ๋‹ค! ์•ž์œผ๋กœ ์ง€์†์ ์ธ ์—…๋ฐ์ดํŠธ๋ฅผ ํ†ตํ•ด ๊ด€๋ฆฌํ•˜๊ฒ ์Šต๋‹ˆ๋‹ค ๋งŽ์ด ํ™œ์šฉํ•ด์ฃผ์„ธ์š” ๐Ÿ™‚
37
  2. ์ดˆ ๊ฐ•๋ ฅํ•œ Advanced-Bllossom 8B, 70B๋ชจ๋ธ, ์‹œ๊ฐ-์–ธ์–ด๋ชจ๋ธ์„ ๋ณด์œ ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค! (๊ถ๊ธˆํ•˜์‹ ๋ถ„์€ ๊ฐœ๋ณ„ ์—ฐ๋ฝ์ฃผ์„ธ์š”!!)
 
98
  CLI:
99
 
100
  ```bash
101
+ llama-cli --hf-repo Bllossom/llama-3-Korean-Bllossom-70B-gguf-Q4_K_M --model bllossom_llama3_70b.Q4_K_M.gguf -p "์„œ์šธ๊ณผํ•™๊ธฐ์ˆ ๋Œ€ํ•™๊ต ์ž„๊ฒฝํƒœ ๊ต์ˆ˜๋Š” ์–ด๋–ค์—ฐ๊ตฌ๋ฅผํ•˜๋‹ˆ?"
102
  ```
103
 
104
  Server:
105
 
106
  ```bash
107
+ llama-server --hf-repo Bllossom/llama-3-Korean-Bllossom-70B-gguf-Q4_K_M --model bllossom_llama3_70b.Q4_K_M.gguf -c 2048
108
  ```
109
 
110
  Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
111
 
112
  ```
113
+ git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m bllossom_llama3_70b.Q4_K_M.gguf -n 128
114
  ```
115
 
116