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
+Mistral-Nemo-Instruct-2407.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Instruct-2407.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Instruct-2407.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Instruct-2407.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Instruct-2407.q8_p.gguf filter=lfs diff=lfs merge=lfs -text

Mistral-Nemo-Instruct-2407.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a9581ae7a87e5727aa1b0670f439ffe2a31a4bcb38ca201f9cd76ac975d31ae
+size 24504276672

Mistral-Nemo-Instruct-2407.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85153681b88afdd785c460aacd3cfa65cd12f727f1e0a65b14856673b96949bb
+size 10400110272

Mistral-Nemo-Instruct-2407.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a4b4fcf19db2a71ae8714a52e0472461978c98875de57b2aede9c4c1f4b5fc7
+size 11639559872

Mistral-Nemo-Instruct-2407.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbff597764ab63f41219a350705099ee89511e48808316597f2a5abdc80d7db8
+size 14280660672

Mistral-Nemo-Instruct-2407.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:824229be17606dd8177fc91c1d330b065bc4f3de2873eab614376b988dcbf48a
+size 13022369472

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 22, 16:52:57