Hugging Face's logo

ZeroWw
/
GLM-Z1-9B-0414-GGUF

Text Generation
GGUF
English
conversational
Model card Files
xet
Community
1
ZeroWw commited on
Commit
e846d73
·
verified ·
1 Parent(s): 65fa77e

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. .gitattributes +6 -0
  2. GLM-Z1-9B-0414.f16.gguf +3 -0
  3. GLM-Z1-9B-0414.q5_k.gguf +3 -0
  4. GLM-Z1-9B-0414.q6_k.gguf +3 -0
  5. GLM-Z1-9B-0414.q8_0.gguf +3 -0
  6. GLM-Z1-9B-0414.q8_p.gguf +3 -0
  7. GLM-Z1-9B-0414.q8q4.gguf +3 -0
  8. README.md +17 -0
.gitattributes CHANGED
@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ GLM-Z1-9B-0414.f16.gguf filter=lfs diff=lfs merge=lfs -text
37
+ GLM-Z1-9B-0414.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
38
+ GLM-Z1-9B-0414.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
39
+ GLM-Z1-9B-0414.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
40
+ GLM-Z1-9B-0414.q8_p.gguf filter=lfs diff=lfs merge=lfs -text
41
+ GLM-Z1-9B-0414.q8q4.gguf filter=lfs diff=lfs merge=lfs -text
GLM-Z1-9B-0414.f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adea96bf0b5f0c490502986bc6cf96f116fcb2a9e03a62bd85aacf8f935077ca
3
+ size 18811581824
GLM-Z1-9B-0414.q5_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a377a5121fbbecc8139364b8dae332e7255642c9b2df4292521b022cc90681a
3
+ size 8597960064
GLM-Z1-9B-0414.q6_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eb6bb92b9d599e077f9adbc6cd6c27303c465b8a209d80ab9e3cf259f921ebd
3
+ size 9731241344
GLM-Z1-9B-0414.q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf772dd31b21bf4e589306ae8217da7df376fbbb355a6726ecb20c96eb791b79
3
+ size 11163530624
GLM-Z1-9B-0414.q8_p.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:263ef138c25ee58558d7af94a475fdfacb60a85079dd10bb356694cbce10bfe8
3
+ size 9999611264
GLM-Z1-9B-0414.q8q4.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:295cff39b18ae99ddd2cec8439ec3e150208d53f8ed72fa361e84ae5986fdbf2
3
+ size 6627292544
README.md ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: mit
4
+ language:
5
+ - en
6
+ pipeline_tag: text-generation
7
+ ---
8
+
9
+ My own (ZeroWw) quantizations.
10
+ output and embed tensors quantized to f16.
11
+ all other tensors quantized to q5_k or q6_k.
12
+
13
+ Result:
14
+ both f16.q6 and f16.q5 are smaller than q8_0 standard quantization
15
+ and they perform as well as the pure f16.
16
+
17
+ Updated on: Sun May 11, 10:10:38