Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ 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
+gemma-2-2b-it.f16.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-2b-it.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-2b-it.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-2b-it.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-2b-it.q8_p.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: Thu Aug 01, 10:58:32

gemma-2-2b-it.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7edd84a0e2c29598c2baa87b3bd9a8687463498a9f31696484beefad03208e57
+size 5235213920

gemma-2-2b-it.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c5892ff1c6741dbda148ec156d40ecfe8f7da546c7d2d830492885900ce26ec
+size 2619086432

gemma-2-2b-it.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16bf3ce632a13bd1f0d528a51243b6aa2ff1319d697c2035cd26157622c32df5
+size 2847200864

gemma-2-2b-it.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad7ed5d441e9b05aaa973d2f4df841e00ff6574b6086151ca7f64d786650ac72
+size 3337455200

gemma-2-2b-it.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e943e00b329d9d23133850e45d8fea9d8bb36c28754c61dbbb288f51e86efe78
+size 2784495200