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-abliterated.f16.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-2b-it-abliterated.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-2b-it-abliterated.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-2b-it-abliterated.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-2b-it-abliterated.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: Fri Aug 02, 18:47:03

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf22c93213266dbdeeb53cc42bc26418dbdbbfc5d400a542ae18aa9408fd3032
+size 5235213920

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf0968dcd1fd949536ec3ddd5699f57d5522c6569dc7c4f66f07e76a639da4a
+size 2619086432

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:855693b6e2cba3439cefa509f6ec3160d274c8942165101586c62c3fea8e8dd6
+size 2847200864

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f3397136b1cb45e4c2edfbfd07fff24d957080aebfd3a972e94045b384debd5
+size 3337455200

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1502949e22176f0dfbcfc2e11bebd4b50182630cd23fa87abdcbf26a054d5135
+size 2784495200