feat: 4-bit quantized model

Signed-off-by: Kai Xu <xuk@ibm.com>

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

config.json

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

merlinite-7b-lab-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ca044d727db34750e1aeb04e3b18c3cf4a8c064a9ac96cf00448c506631d16c
+size 4368484992