Hugging Face's logo

venketh
/
gpt4-x-vicuna-13b-gguf-imatrix

Model card Files Community
Venkatesh Srinivas commited on
Commit
caebf6c
•
1 Parent(s): 6dd9de3

Swap Q3_K_L for new IQ4_XS quantization

Browse files
Files changed (1) hide show
  1. gpt4-x-vicuna-13B.gguf.q3_K_L.bin → gpt4-x-vicuna-13B.gguf.IQ4_XS.bin +2 -2
gpt4-x-vicuna-13B.gguf.q3_K_L.bin → gpt4-x-vicuna-13B.gguf.IQ4_XS.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a57e5edd5149365c2f9c7fe3aae89ec7d8f5775518dce1a1a4889d3f1528fbf8
3
- size 6929565888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69a9e57d69e78c1d2c440b8e7ef8f7213f95964c17dcaa1d9c402cdafc8b543
3
+ size 6964228864