Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ 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
+Samantha-Qwen-2-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Samantha-Qwen-2-7B.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+Samantha-Qwen-2-7B.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Samantha-Qwen-2-7B.q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+
+---
+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.  

Samantha-Qwen-2-7B.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55d7b4bee5b1488b5df05c2066b2070536285e14205792229bad9e0702bbd6c6
+size 15237850656

Samantha-Qwen-2-7B.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3bc7f2d3a3dff60c0087db4db1e0d29f313fe893ddb9d09b46205b631e5325b
+size 6803064352

Samantha-Qwen-2-7B.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77eb16f30b5ae6056a66a6fb0720c7acf485a75479c3b0b0428694665352c38f
+size 7540049440

Samantha-Qwen-2-7B.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dd0b0dc0038d03bc9f3d959930c866a6f5ca1c67c7a5ba04d1f24574dc5ce59
+size 9120392736