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
+codegeex4-all-9b.f16.gguf filter=lfs diff=lfs merge=lfs -text
+codegeex4-all-9b.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+codegeex4-all-9b.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+codegeex4-all-9b.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+codegeex4-all-9b.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: Sat Jul 13, 09:06:20

codegeex4-all-9b.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75c7e0b4f8b5ced54427ba98270ab993b507419021b455e5cccbefbf2fcc6b65
+size 18806965376

codegeex4-all-9b.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080e00a11e9935074b151438cfd47d35aa4d7461218811a5c842070e5adda084
+size 8690828416

codegeex4-all-9b.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:229fc8bc3b69e1ae288fdf9fd9a231e7c57938b2468067771cbd062c870dbe8d
+size 9726624896

codegeex4-all-9b.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47812fca3b796aea44158c18627e1a9c671ceb8452154b5582de4c0c2cc22983
+size 11158914176

codegeex4-all-9b.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8f173b49ce9d00bc8f19041e79b13059f6c2dc957420b5140245fc441bc64f5
+size 9994994816