feat: 4-bit quantized model

Signed-off-by: Kai Xu <[email protected]>

.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
+granite-7b-lab-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,3 @@
+{
+    "model_type": "llama"
+}

granite-7b-lab-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6adeaad8c048b35ea54562c55e454cc32c63118a32c7b8152cf706b290611487
+size 4081050336