Upload folder using huggingface_hub

.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-3.1-8b-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,17 @@
+
+---
+license: mit
+language:
+- en
+pipeline_tag: text-generation
+---
+
+My own (ZeroWw) quantizations.
+output and embed tensors quantized to f16.
+all other tensors quantized to q5_k or q6_k.
+
+Result:
+both f16.q6 and f16.q5 are smaller than q8_0 standard quantization
+and they perform as well as the pure f16.
+
+Updated on: Sun Jan 05, 17:19:32

granite-3.1-8b-instruct.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c9608b4d93ab55b76172b6d840c7e2b13c2ebedc12588b0d3958d5b97715db5
+size 16344105632