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
+L3-SthenoMaid-8B-V1.f16.gguf filter=lfs diff=lfs merge=lfs -text
+L3-SthenoMaid-8B-V1.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+L3-SthenoMaid-8B-V1.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+L3-SthenoMaid-8B-V1.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+L3-SthenoMaid-8B-V1.q8_p.gguf filter=lfs diff=lfs merge=lfs -text

L3-SthenoMaid-8B-V1.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bccc5c40e8eb8af9a0c66605796090290e9e974b6377479753af38e26156279c
+size 16068890944

L3-SthenoMaid-8B-V1.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1855b5840e9b06fac33aab89144d708bef8b679fc62958583c76676d548d69e
+size 7042224448

L3-SthenoMaid-8B-V1.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e4abcbc1195fb151d18c45bda3fc306c35a006759da4490d86e98ac67eae607
+size 7835472192

L3-SthenoMaid-8B-V1.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2005012eee8053e4112dc24d733a67b4c62f2e6e1cdb8e1dcd07f0e66163c3e
+size 9525776704

L3-SthenoMaid-8B-V1.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbf5607b480d0968d245a6f0d9f90a35e26506ddd4ceb0e18755aeb0f80ca875
+size 8540770624

README.md

@@ -0,0 +1,16 @@
+
+---
+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.
+
+Updated on: Thu Jul 18, 10:07:00