eachadea commited on
Commit
40313ef
1 Parent(s): 414c1be

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -7,6 +7,7 @@ tags:
7
  ---
8
  Converted for use with [llama.cpp](https://github.com/ggerganov/llama.cpp)
9
  ---
 
10
  - 4-bit quantized
11
  - Needs ~6GB of CPU RAM
12
  - Won't work with alpaca.cpp or old llama.cpp (new ggml format requires latest llama.cpp)
 
7
  ---
8
  Converted for use with [llama.cpp](https://github.com/ggerganov/llama.cpp)
9
  ---
10
+ - Based on AlekseyKorshuk/vicuna-7b
11
  - 4-bit quantized
12
  - Needs ~6GB of CPU RAM
13
  - Won't work with alpaca.cpp or old llama.cpp (new ggml format requires latest llama.cpp)