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
+palmer-004-turbo.f16.gguf filter=lfs diff=lfs merge=lfs -text
+palmer-004-turbo.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+palmer-004-turbo.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+palmer-004-turbo.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+palmer-004-turbo.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: Wed Jul 17, 16:32:44

palmer-004-turbo.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd64dfcd5f4663e1018b20d70a27fe6c55b37d62e08c8aedcb05a9d82aac2af
+size 1028009440

palmer-004-turbo.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:646bb3fe1af6a3157a27b1511de9921b0e5d7daddb689f9cdb36ee0af92dbe00
+size 490950112

palmer-004-turbo.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8300e2d53caca7fa6c64cb4c3344e7c28652f9c748c1afc818f1005623e97440
+size 538160608

palmer-004-turbo.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049a6e22aff514f2789e961f96463fd491fb9d8bc068300f234e0011c33ce9e5
+size 638725600

palmer-004-turbo.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4583a247d584c12b169c170a8f3dec41ec4c22692d13aa9facfd4f51a0454462
+size 546565600