llamafile
English
GGUF
jartine commited on
Commit
43f6b44
·
verified ·
1 Parent(s): 0eab25b

Quantize BF16 with llamafile-0.8.17

Browse files
TinyLlama-1.1B-Chat-v1.0.BF16.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e4d27b80d0f485c5be91f641619f78950cce92439812584ad48a2b8ad759f7f
3
- size 2370779230
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7060208eb3984ae86a5906134d2df6275ee3f3c05a044e9f3460b200d262fec1
3
+ size 2371303518