Update README.md
Browse files
README.md
CHANGED
@@ -31,7 +31,7 @@ Although llama.cpp can be used to reduce the size of the file with various quant
|
|
31 |
- ใใใP๏ผ--top_p๏ผ: ใใฎๅคใใใใซไฝใ่จญๅฎใใใใจใงใใขใใซใ่ๆ
ฎใใๅ่ชใฎ็ฏๅฒใ็ญใใใใไธ่ฒซๆงใฎใใใใญในใใ็ๆใใใใใซใชใใพใใ
|
32 |
- ็ๆใใๅ่ชๆฐ๏ผ-n๏ผ: ใใฎๅคใๆธใใใใจใงใใขใใซใ็ๆใใใใญในใใฎ้ทใใ็ญใใใไธ่ฆใช่ฟฝๅ ใใญในใใฎ็ๆใ้ฒใใใจใใงใใพใใ-1 = ็ก้ๅคงใ-2 = ๆ่ใๆบใใใใใพใงใ
|
33 |
|
34 |
-
ไปฅไธใฏllama.cppใฎไฝ่
(ggerganov)
|
35 |
- -e (ๆน่ก\nใใจในใฑใผใ)
|
36 |
- --temp 0 (ๆใ็ขบ็ใฎ้ซใใใผใฏใณใฎใฟใ้ธๆ)
|
37 |
- --repeat-penalty 1.0 (็นฐใ่ฟใใใใซใใฃใใชใใๆ็คบ่ชฟๆดๆธใขใใซใงใใใใใใฎใฏใๆฑบใใฆ่ฏใ่ใใจใฏ่จใใชใใ)
|
@@ -42,7 +42,7 @@ Adjust the following parameters as needed
|
|
42 |
- Top P (--top_p): Setting this value even lower will narrow the range of words considered by the model and produce more consistent text.
|
43 |
- Number of words to generate (-n): Reducing this value will shorten the length of text generated by the model and prevent the generation of unnecessary additional text. -1 = infinity(default), -2 = until context filled.
|
44 |
|
45 |
-
The following are the recommended parameters by the author of llama.cpp(ggerganov)
|
46 |
- -e (escape newlines (\n))
|
47 |
- --temp 0(pick most probable tokens)
|
48 |
- --repeat-penalty 1.0(disable repetition penalty (it's never a good idea to have this with instruction tuned models)
|
|
|
31 |
- ใใใP๏ผ--top_p๏ผ: ใใฎๅคใใใใซไฝใ่จญๅฎใใใใจใงใใขใใซใ่ๆ
ฎใใๅ่ชใฎ็ฏๅฒใ็ญใใใใไธ่ฒซๆงใฎใใใใญในใใ็ๆใใใใใซใชใใพใใ
|
32 |
- ็ๆใใๅ่ชๆฐ๏ผ-n๏ผ: ใใฎๅคใๆธใใใใจใงใใขใใซใ็ๆใใใใญในใใฎ้ทใใ็ญใใใไธ่ฆใช่ฟฝๅ ใใญในใใฎ็ๆใ้ฒใใใจใใงใใพใใ-1 = ็ก้ๅคงใ-2 = ๆ่ใๆบใใใใใพใงใ
|
33 |
|
34 |
+
ไปฅไธใฏllama.cppใฎไฝ่
(ggerganov)ใซใใ[ๆจๅฅจใใฉใกใผใฟใผ](https://huggingface.co/google/gemma-7b-it/discussions/38#65d7b14adb51f7c160769fa1)ใงใ
|
35 |
- -e (ๆน่ก\nใใจในใฑใผใ)
|
36 |
- --temp 0 (ๆใ็ขบ็ใฎ้ซใใใผใฏใณใฎใฟใ้ธๆ)
|
37 |
- --repeat-penalty 1.0 (็นฐใ่ฟใใใใซใใฃใใชใใๆ็คบ่ชฟๆดๆธใขใใซใงใใใใใใฎใฏใๆฑบใใฆ่ฏใ่ใใจใฏ่จใใชใใ)
|
|
|
42 |
- Top P (--top_p): Setting this value even lower will narrow the range of words considered by the model and produce more consistent text.
|
43 |
- Number of words to generate (-n): Reducing this value will shorten the length of text generated by the model and prevent the generation of unnecessary additional text. -1 = infinity(default), -2 = until context filled.
|
44 |
|
45 |
+
The following are the [recommended parameters](https://huggingface.co/google/gemma-7b-it/discussions/38#65d7b14adb51f7c160769fa1) by the author of llama.cpp(ggerganov)
|
46 |
- -e (escape newlines (\n))
|
47 |
- --temp 0(pick most probable tokens)
|
48 |
- --repeat-penalty 1.0(disable repetition penalty (it's never a good idea to have this with instruction tuned models)
|