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
+SOLAR-10.7B-Instruct-v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text
+SOLAR-10.7B-Instruct-v1.0.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+SOLAR-10.7B-Instruct-v1.0.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+SOLAR-10.7B-Instruct-v1.0.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+SOLAR-10.7B-Instruct-v1.0.q8_p.gguf filter=lfs diff=lfs merge=lfs -text

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: Sun Jul 28, 03:31:13

SOLAR-10.7B-Instruct-v1.0.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c22ee31c13a587d91d408170fd70b50bf0f5e314494afdbb1a30a5e4862131
+size 21464587776

SOLAR-10.7B-Instruct-v1.0.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f8ed508bdec483442cf9b32d69575b88c0c88cda92b57c170619d31a0c1883d
+size 7924588032

SOLAR-10.7B-Instruct-v1.0.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7cc85fee871047562d3f69b71d1f45123478ae70bbe8d18b52156d44b394054
+size 9114459648

SOLAR-10.7B-Instruct-v1.0.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5ec2b0129bb1d52ae48c32c801299676e6024935f91c317c556fc2f392d3b7
+size 11649916416

SOLAR-10.7B-Instruct-v1.0.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43065ba56ad10a528f34dac57b23fb13d07ea3d6ebfad2d4cbc95a099f27dd17
+size 11404156416