Update README.md
Browse files
README.md
CHANGED
@@ -32,7 +32,7 @@ language:
|
|
32 |
|
33 |
LLaMa 65B converted to ggml via LLaMa.cpp, then quantized to 4bit.
|
34 |
|
35 |
-
Legacy is for llama.cpp setups older than https://github.com/ggerganov/llama.cpp/pull/
|
36 |
|
37 |
I recommend the following settings when running as a good starting point:
|
38 |
```main.exe -m ggml-LLaMa-65B-q4_0.bin -n -1 -t 32 -c 2048 --temp 0.7 --repeat_penalty 1.2 --mirostat 2 --interactive-first --color```
|
|
|
32 |
|
33 |
LLaMa 65B converted to ggml via LLaMa.cpp, then quantized to 4bit.
|
34 |
|
35 |
+
Legacy is for llama.cpp setups older than https://github.com/ggerganov/llama.cpp/pull/1508, the regular is faster but does not work on old versions.
|
36 |
|
37 |
I recommend the following settings when running as a good starting point:
|
38 |
```main.exe -m ggml-LLaMa-65B-q4_0.bin -n -1 -t 32 -c 2048 --temp 0.7 --repeat_penalty 1.2 --mirostat 2 --interactive-first --color```
|