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
+Yi-1.5-9B-32K.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-1.5-9B-32K.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-1.5-9B-32K.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-1.5-9B-32K.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.

Yi-1.5-9B-32K.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5091a9f62120175a2700289c2d8fb13f02c6ce8e918d2e87fecb9b466819ee5b
+size 17661112128

Yi-1.5-9B-32K.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7314765a679258afc17e7feac8b1e532d9db9c784384105125d29da6552ef90
+size 6911569728

Yi-1.5-9B-32K.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d2a1e28e30db44f8a1cc758b6c21e1727ddef2c9fc51c02a0605d4a12e3f572
+size 7864135488

Yi-1.5-9B-32K.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0088387e1f664776469231a1784227876af98edbda9c8e9dae75d413d6f3fc1
+size 9875435328