700B

README.md

@@ -8,4 +8,7 @@ This is a GGUF quantization of the [Poro-34B](https://huggingface.co/LumiOpen/Po
 
 Please refer to that repository's model card for details.
 
-The conversion was done with [llama.cpp](https://github.com/ggerganov/llama.cpp) version `bb50a792ec2a49944470c82694fa364345e95170`.
+The current revision is a quantization of the 700B token checkpoint.
+
+The conversion was done with [llama.cpp](https://github.com/ggerganov/llama.cpp) version b1641 (6744dbe924a317e3e2a5a2a4a2037061b2223449)
+on a Google Compute machine generously sponsored by [Valohai](https://valohai.com/).

ggml-model-Q3_K.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11bdb7c81558d73296bb060c094d4e4554133e13646ce10ee33d944240e471d3
+oid sha256:05854a5ef2b53e2174b6d90e8f4d459ada8ab03213a153eef95ee3b893b5f3ad
 size 18477373600

ggml-model-Q4_K.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b80de89fe25d5e35c08a4566a01171f5b209d0d665e9d1c003001589087ca46
+oid sha256:1cd5c3ef547904f513855864e2ba088d0b7631abc3cce7a7dbf90b8e8976dea6
 size 22439901344

ggml-model-Q5_K.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8b04b86e9a486e674c44c17bbea995bc51f2e26ef15189e5bb4776feb3d71f5
+oid sha256:1496c6841aa49b8731e4b0bcc91bac3a8bf1c2f03468b234715468de0b29088d
 size 26113472672