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
+MixTAO-7Bx2-MoE-v8.1.f16.gguf filter=lfs diff=lfs merge=lfs -text
+MixTAO-7Bx2-MoE-v8.1.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+MixTAO-7Bx2-MoE-v8.1.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+MixTAO-7Bx2-MoE-v8.1.q8_0.gguf filter=lfs diff=lfs merge=lfs -text

MixTAO-7Bx2-MoE-v8.1.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3d1fb572f786afd67dbb59f8a7741156f587560bfe4d4ab75aa0681442660ba
+size 25760072928

MixTAO-7Bx2-MoE-v8.1.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d02d6debf23e0372dee1244797eec60dd65f0dc524fabd30cfc9c368044edecc
+size 9459434720

MixTAO-7Bx2-MoE-v8.1.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b865a5b4cfe5a5e9caafb15c669cb68830f75f437ac18b1a7df8d8849acc028b
+size 10876585184

MixTAO-7Bx2-MoE-v8.1.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cde692a6e35bc4ed5249d550f947cc040543577071adf341ed7a24161dcc041
+size 13932135648

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.