CRD716 commited on
Commit
6fa3d89
·
1 Parent(s): 8ebb55e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
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/1405, 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```
 
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```