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
+Llama-3-8B-Instruct-Gradient-1048k.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-Gradient-1048k.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-Gradient-1048k.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-Gradient-1048k.q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3-8B-Instruct-Gradient-1048k.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14306135b6d8afa069d3604f0386fe9bf4d2070589a56cd41168145f5e93115e
+size 16068890912

Llama-3-8B-Instruct-Gradient-1048k.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7a47142439baf7b4c8c58237e352fd91b306a60650fd3e6d748c9053e32ad86
+size 7042224416

Llama-3-8B-Instruct-Gradient-1048k.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:455467581d725df8b947a7b568d1a7f0cf37a22884696d3fa9b2c91a74ae5f09
+size 7835472160

Llama-3-8B-Instruct-Gradient-1048k.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea7b17338af5bdaf825cf478ad5b1a69ef32f9a17c8561843afff2f389708ffb
+size 9525776672

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.