add full f16 gguf and quantized versions

Adds the fully `f16` precision model converted to `.gguf` and the two quantized versions (i.e., the `Q1_3` and `Q2_2`).

.gitattributes

@@ -33,3 +33,6 @@ 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
+model_f16.gguf filter=lfs diff=lfs merge=lfs -text
+model_quant_Q1_3.gguf filter=lfs diff=lfs merge=lfs -text
+model_quant_Q2_2.gguf filter=lfs diff=lfs merge=lfs -text

model_f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fc35e25de3315d5c5f7e2f8e4d09af4cfd84c66b12a9927c64d9640195d935c
+size 6650487168

model_quant_Q1_3.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93397569b7562df531d823defc54749ba81046568f3ff29c3db87be41f9c81b4
+size 765841184

model_quant_Q2_2.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0b04449fabec0ef2ce39fb311c4e203e50f06a2e81f3d6764f7c5869fb24a38
+size 916849184