Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,9 @@ 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
+Marco-o1.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Marco-o1.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+Marco-o1.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Marco-o1.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Marco-o1.q8_p.gguf filter=lfs diff=lfs merge=lfs -text
+Marco-o1.q8q4.gguf filter=lfs diff=lfs merge=lfs -text

Marco-o1.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c968f84dccf2128be3a3bcc54225a645dfc0d357db188d87b21018843864037
+size 15237851296

Marco-o1.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96132d7fb0d0bcd95d76f48da49760c53e68c30e0675b73ae377eee6e9871605
+size 6803064992

Marco-o1.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659e23a55ce664afc04b68cc22c719c5ce4335ca078855a43542a479ef18ecd9
+size 7540050080

Marco-o1.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a2f6eb9ee246598821dc9743b79d3b5297c9c2f0fec76bbc15eeee83988369
+size 9120393376

Marco-o1.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f4c14c33acd90c4635785707b150ca42886c9921f16a207518a57b7e1ba6bd7
+size 8098523296

Marco-o1.q8q4.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9d4bce2c0fc776370b8d6f5f42d2ffe33829b6b60129f498bc226e0fa46453d
+size 5087561888

README.md

@@ -0,0 +1,17 @@
+
+---
+license: mit
+language:
+- en
+pipeline_tag: text-generation
+---
+
+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: Wed Nov 27, 12:44:58