eachadea
/

legacy-ggml-vicuna-13b-4bit

Text Generation

text-generation-inference

Model card Files Files and versions Community

eachadea commited on Apr 3, 2023

Commit

33d5856

•

1 Parent(s): f1d7ec5

Update README.md

Files changed (1) hide show

README.md +5 -0

README.md CHANGED Viewed

@@ -1,3 +1,8 @@
 ---
 tags:
 - vicuna

+Converted for use with [llama.cpp](https://github.com/ggerganov/llama.cpp)
+---
+- 4-bit quantized
+- Needs ~10GB of CPU RAM
 ---
 tags:
 - vicuna