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
+llama3-turbcat-instruct-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text
+llama3-turbcat-instruct-8b.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+llama3-turbcat-instruct-8b.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+llama3-turbcat-instruct-8b.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+llama3-turbcat-instruct-8b.q8_p.gguf filter=lfs diff=lfs merge=lfs -text

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: Thu Jul 18, 10:07:21

llama3-turbcat-instruct-8b.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4df4a137f91dac36f78feb3329363418294714472c25d19e9cde462f03ce37b5
+size 16068891104

llama3-turbcat-instruct-8b.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96f8df37ebc67550b5e5591cb686e98f3a6588ebf04b7148c924eecc0981ea6f
+size 7042224608

llama3-turbcat-instruct-8b.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ebaad772b35f4aaee8d3c4d2f16a057104896b3a4214f058b9359c8db8c3fa
+size 7835472352

llama3-turbcat-instruct-8b.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e4263056f8ff2bca124796fe900f0d5017902112e95a780c714de953d2bda5d
+size 9525776864

llama3-turbcat-instruct-8b.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b09129aa88f3eaad58cf0572f8b8babbaa8b1c08e77e59acb49bb44c192090c0
+size 8540770784