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
+Meta-Llama-3.1-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct.q8_p.gguf filter=lfs diff=lfs merge=lfs -text

Meta-Llama-3.1-8B-Instruct.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993c3be009040f165d6ced6e6374276441c128a82672db2ca5761a14286ac76f
+size 16068891296

Meta-Llama-3.1-8B-Instruct.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8a0d47743608c99029646132107c3abb395c07c26a05441a653817e535676b9
+size 7042224800

Meta-Llama-3.1-8B-Instruct.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e14bcbb5cc5e6e05905feb30ad3ed2f1c55e1f8c49d384e41f1933bcf9aef16
+size 7835472544

Meta-Llama-3.1-8B-Instruct.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1a80c17c3034cc261e290013975e34380a438a9a5630792b7c1cfec184a8170
+size 9525777056

Meta-Llama-3.1-8B-Instruct.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d36aafdc1d822f932f3fd3ddc18296628764c5e43f153e9c02b29f5c4525cf2a
+size 8540770976

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: Sat Jul 27, 15:17:21