Add GGUF and Q4 version of the model for llama.cpp

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+ggml-model-f16.gguf filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -1,6 +1,3 @@
 {
-  "</s>": 2,
-  "<s>": 1,
-  "<unk>": 0,
   "[PAD]": 32000
 }

ggml-model-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2990323139c845727dae835865fd5b81b4d2b72521dda2fded2d0c4dcb731092
+size 26033323872

ggml-model-q4_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f2cb609b0d4d3f819180d98d8254b5ebdaafedfa0f84410492325b333ef664d
+size 7365841760