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
+h2o-danube3-4b-chat.f16.gguf filter=lfs diff=lfs merge=lfs -text
+h2o-danube3-4b-chat.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+h2o-danube3-4b-chat.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+h2o-danube3-4b-chat.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+h2o-danube3-4b-chat.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: Tue Jul 16, 07:53:41

h2o-danube3-4b-chat.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3562addece4ee2a8acaace22642a58ece4d491b9f3007a817b82b1a63a65c57c
+size 7924786656

h2o-danube3-4b-chat.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b75110d9112b9573325cb05ef031d4a07a43dcc4bf3373f5e27f4f0e7a72219e
+size 3116223456

h2o-danube3-4b-chat.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d5d3737bda131a7ffda6605019f2c10da13c3019edbd9fbe6a8b1b41b944be
+size 3541196256

h2o-danube3-4b-chat.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e4c979ee24452df888ae390764c131448b70bd402614326491b4538325272d
+size 4441138656

h2o-danube3-4b-chat.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d42b5940d26131fcd70b21e229a966065f03d8a75d1b905cda2e143c7b4a0c2b
+size 4210738656