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
+L3-8B-Stheno-v3.3-32K.f16.gguf filter=lfs diff=lfs merge=lfs -text
+L3-8B-Stheno-v3.3-32K.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+L3-8B-Stheno-v3.3-32K.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+L3-8B-Stheno-v3.3-32K.q8_0.gguf filter=lfs diff=lfs merge=lfs -text

L3-8B-Stheno-v3.3-32K.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475b5304172f50ed432c36243d75ab80b246fa22f781e1e2777e811b58df1d9b
+size 16068891040

L3-8B-Stheno-v3.3-32K.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02a4fcb3ff36c75842cf0541e7a5fb6f0f459ccf1ccb5a188437612aa506d0f4
+size 7042224544

L3-8B-Stheno-v3.3-32K.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59ba3723434ab814622235cae8af220dff7911e6078572a0cc013cbadf8d2c7
+size 7835472288

L3-8B-Stheno-v3.3-32K.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:516edce0700ac52631ce5a7697cc36755f44dedb2430ef64c752eb58ed0aea46
+size 9525776800

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.