Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,9 @@ 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
+Qwen3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B.q8_p.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B.q8q4.gguf filter=lfs diff=lfs merge=lfs -text

Qwen3-8B.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc8b6ba7073bf9543abfa30f33103170aba5c9ccda3d64944c7484b4839e2fd
+size 16388043968

Qwen3-8B.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c4ca43a3c2ad33f5c85d571594f719b77a2c522f07e1b4a63c3212ab1929738
+size 7402075328

Qwen3-8B.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59eb7d9eda015ae8f5d6f5bd47da0f40e86cb735381fed24a95df8e640391011
+size 8194208960

Qwen3-8B.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb93c06d25b22488a0fa5cc0970b64b89f1249d944847500afd63052eecb54e7
+size 9876387008

Qwen3-8B.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e15cc67ee93f33145ae47ed35e390c88af210f55e14fa3f91cc599a05a64342d
+size 8709518528

Qwen3-8B.q8q4.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab2d62ec1bf726553e8a802b02615dd2786c80b96858cc50bf44677cceb307c
+size 5489669312

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: Tue Apr 29, 06:53:03