teddylee777 commited on
Commit
aa24b55
β€’
1 Parent(s): f4771da

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -15,7 +15,7 @@ license_name: llama3
15
  license_link: https://llama.meta.com/llama3/license
16
  ---
17
 
18
- - Original model is [beomi/Llama-3-Open-Ko-8B-Instruct-preview](https://huggingface.co/beomi/Llama-3-Open-Ko-8B-Instruct-preview)
19
  - quantized using [llama.cpp](https://github.com/ggerganov/llama.cpp)
20
 
21
 
@@ -24,7 +24,7 @@ license_link: https://llama.meta.com/llama3/license
24
  Modelfile
25
 
26
  ```
27
- FROM Llama-3-Open-Ko-8B-Instruct-preview-Q8_0.gguf
28
 
29
  TEMPLATE """{{- if .System }}
30
  <s>{{ .System }}</s>
@@ -34,7 +34,7 @@ TEMPLATE """{{- if .System }}
34
  <s>Assistant:
35
  """
36
 
37
- SYSTEM """μΉœμ ˆν•œ μ±—λ΄‡μœΌλ‘œμ„œ μƒλŒ€λ°©μ˜ μš”μ²­μ— μ΅œλŒ€ν•œ μžμ„Έν•˜κ³  μΉœμ ˆν•˜κ²Œ λ‹΅ν•˜μž. λͺ¨λ“  λŒ€λ‹΅μ€ ν•œκ΅­μ–΄(Korean)으둜 λŒ€λ‹΅ν•΄μ€˜."""
38
 
39
  PARAMETER temperature 0
40
  PARAMETER num_predict 3000
 
15
  license_link: https://llama.meta.com/llama3/license
16
  ---
17
 
18
+ - Original model is [beomi/Llama-3-Open-Ko-8B](https://huggingface.co/beomi/Llama-3-Open-Ko-8B)
19
  - quantized using [llama.cpp](https://github.com/ggerganov/llama.cpp)
20
 
21
 
 
24
  Modelfile
25
 
26
  ```
27
+ FROM Llama-3-Open-Ko-8B-Q8_0.gguf
28
 
29
  TEMPLATE """{{- if .System }}
30
  <s>{{ .System }}</s>
 
34
  <s>Assistant:
35
  """
36
 
37
+ SYSTEM """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions."""
38
 
39
  PARAMETER temperature 0
40
  PARAMETER num_predict 3000