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
+glm-4-9b-chat.BF16.gguf filter=lfs diff=lfs merge=lfs -text
+glm-4-9b-chat.f16.gguf filter=lfs diff=lfs merge=lfs -text
+glm-4-9b-chat.q5.gguf filter=lfs diff=lfs merge=lfs -text
+glm-4-9b-chat.q6.gguf filter=lfs diff=lfs merge=lfs -text
+glm-4-9b-chat.q8.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.

glm-4-9b-chat.BF16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bede35b3f1692c31220c8ba0d69f67cd31a69e2486e3d4bd0b506ced8794923a
+size 18806965440

glm-4-9b-chat.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceccb3a36d4081e7de4e874bb75a731bf4d899e97162893ff356f4aa1627dbd1
+size 18806965440

glm-4-9b-chat.q5.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa070d63827d9e2e36b85109893e0330cd7adf7905d88780e8c0b45719c2462
+size 8690828480

glm-4-9b-chat.q6.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13d8e8087317cab94d14d18ccb779cc98f359cdd4548b4cb4ed5cfcad748d597
+size 9726624960

glm-4-9b-chat.q8.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:048bc2b4378c49cba944553be29ffae8f2b1e5b84b8a3913db1c17a93c2b85d8
+size 11158914240