Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ 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
+aya-23-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text
+aya-23-8B.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+aya-23-8B.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+aya-23-8B.q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+
+---
+license: mit
+language:
+- en
+---
+
+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.

aya-23-8B.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85cb318c02ead3c3b7dad8c52e0cf418f06dd56b7665fafda894f5b306c9527e
+size 16067226496

aya-23-8B.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881c03282e0ccdb4f70865256ac1f8fdcf700ef7823492ab3b2d44b0d3055354
+size 7040560000

aya-23-8B.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59fa9006d9ef1a1d2221d5d20ed5e8e10f74f8e11d5273542cc54a57c8838ba8
+size 7833807744

aya-23-8B.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26c0cc47e228a1d67a9b12c5e13d8bdce1aa14ef0e9675e2bd92351d229ae94
+size 9524112256