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
+NuminaMath-7B-TIR.f16.gguf filter=lfs diff=lfs merge=lfs -text
+NuminaMath-7B-TIR.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+NuminaMath-7B-TIR.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+NuminaMath-7B-TIR.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+NuminaMath-7B-TIR.q8_p.gguf filter=lfs diff=lfs merge=lfs -text

NuminaMath-7B-TIR.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05fff9d7a0fc4a511c5ae0356654dd60b0e3ab16e7f53cf6a850d520b2974cce
+size 13825218080

NuminaMath-7B-TIR.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:338d6009e5da05c4a1178b16b23ab02e3c606652e04a7c1cde8a7302de9c40ed
+size 5971727904

NuminaMath-7B-TIR.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb6e91367cdbee7ca398c512741d97d3b5d9ec04984ae3d6e2f4bfe3b64a5f3
+size 6663034400

NuminaMath-7B-TIR.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56f034a1e82f23888eba2e62e7eb512004825d132f51ed653698f034259f5614
+size 8133416480

NuminaMath-7B-TIR.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b87761460641f7fa0b78b5aeafa9b12ee37d2ff43410d1426bba1db6685d40a8
+size 7346984480

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: Fri Jul 12, 11:46:49