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
+open_llama_3b_v2.f16.gguf filter=lfs diff=lfs merge=lfs -text
+open_llama_3b_v2.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+open_llama_3b_v2.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+open_llama_3b_v2.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+open_llama_3b_v2.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: Mon Jul 15, 14:32:15

open_llama_3b_v2.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0600429b61c523d4f7dbd4fa15fbfb9ff6f93e7048dd94add93868d0f7153b27
+size 6854036224

open_llama_3b_v2.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d44eebff4ce0fb2dc1a940d975a1dbc13dd34aad2eb339e955586a5a84b6c21
+size 2981076224

open_llama_3b_v2.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a353f8909ecfad165bc38df213b1472425c9ea783f027a3ea8cc77691723fd
+size 3833876224

open_llama_3b_v2.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e160b6e2e0ada9c5f9dee0347a2313783d803a730911dc104a463d569754f8fe
+size 3833876224

open_llama_3b_v2.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36515d9d3bd2578d42c702700f0a8ef09b35afe5e626b00acf1298fe2787b869
+size 3641876224