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
+Moistral-11B-v3.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Moistral-11B-v3.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+Moistral-11B-v3.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Moistral-11B-v3.q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Moistral-11B-v3.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b02e00847c5c80e6d24cbe1418b6b834128da99140369fb7f5b1b8d138dde2dd
+size 21464586528

Moistral-11B-v3.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:236e83341c45486b955df595628fd7fcf9ea8907170cbe0961381db16c0c5762
+size 7924586784

Moistral-11B-v3.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5258e10a6585e4a26a310fdad6d90ae3c67da05ddaf03762b7d6857f91b86eb6
+size 9114458400

Moistral-11B-v3.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d27cbc670973cb8a385c4af052aa68388a41552abb1b77a6617ce73445e90c
+size 11649915168

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: Mon Jul 08, 01:10:10