Hugging Face's logo

basecompute
/
GLM-5.2

Text Generation
basert
apple-silicon
quantized
Model card Files
xet
 Community
fabian-basecompute commited on
Commit
e4facbe
·
0 Parent(s):

GLM-5.2 Q4 BaseRT bundle

Browse files
Files changed (11) hide show
  1. .gitattributes +44 -0
  2. README.md +41 -0
  3. parts/GLM-5.2-Q4.base.part-000 +3 -0
  4. parts/GLM-5.2-Q4.base.part-001 +3 -0
  5. parts/GLM-5.2-Q4.base.part-002 +3 -0
  6. parts/GLM-5.2-Q4.base.part-003 +3 -0
  7. parts/GLM-5.2-Q4.base.part-004 +3 -0
  8. parts/GLM-5.2-Q4.base.part-005 +3 -0
  9. parts/GLM-5.2-Q4.base.part-006 +3 -0
  10. parts/GLM-5.2-Q4.base.part-007 +3 -0
  11. parts/GLM-5.2-Q4.base.part-008 +3 -0
.gitattributes ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
+ parts/GLM-5.2-Q4.base.part-000 filter=lfs diff=lfs merge=lfs -text
37
+ parts/GLM-5.2-Q4.base.part-001 filter=lfs diff=lfs merge=lfs -text
38
+ parts/GLM-5.2-Q4.base.part-002 filter=lfs diff=lfs merge=lfs -text
39
+ parts/GLM-5.2-Q4.base.part-003 filter=lfs diff=lfs merge=lfs -text
40
+ parts/GLM-5.2-Q4.base.part-004 filter=lfs diff=lfs merge=lfs -text
41
+ parts/GLM-5.2-Q4.base.part-005 filter=lfs diff=lfs merge=lfs -text
42
+ parts/GLM-5.2-Q4.base.part-006 filter=lfs diff=lfs merge=lfs -text
43
+ parts/GLM-5.2-Q4.base.part-007 filter=lfs diff=lfs merge=lfs -text
44
+ parts/GLM-5.2-Q4.base.part-008 filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: zai-org/GLM-5.2
4
+ library_name: basert
5
+ pipeline_tag: text-generation
6
+ tags:
7
+ - basert
8
+ - apple-silicon
9
+ - quantized
10
+ ---
11
+
12
+ # GLM-5.2
13
+
14
+ [BaseRT](https://github.com/basecompute/baseRT) `.base` builds of [`zai-org/GLM-5.2`](https://huggingface.co/zai-org/GLM-5.2) for fast local inference on Apple Silicon (Metal).
15
+
16
+ A 78-layer MoE reasoning model with DSA sparse attention and an MTP layer. Q4 needs 512 GB Apple Silicon.
17
+
18
+ ## Files
19
+
20
+ Q4 is 432 GB, past the Hub's per-file ceiling, so it ships as 9 parts of ≤45 GiB under `parts/`.
21
+
22
+ | File | Precision | Size |
23
+ |------|-----------|------|
24
+ | `parts/GLM-5.2-Q4.base.part-000` … `part-008` | 4-bit | 432 GB total |
25
+
26
+ Reassemble before use:
27
+
28
+ ```sh
29
+ cat parts/GLM-5.2-Q4.base.part-* > GLM-5.2-Q4.base
30
+ shasum -a 256 GLM-5.2-Q4.base # expect e7cf483188806908f290a6eed1d96ec6a974cb3d4751a867d5c67a317646c230
31
+ ```
32
+
33
+ ## Usage
34
+
35
+ ```bash
36
+ curl -LsSf https://basecompute.co/install.sh | sh
37
+ basert pull basecompute/GLM-5.2
38
+ basert chat basecompute/GLM-5.2
39
+ ```
40
+
41
+ Released under the mit license, inherited from the base model.
parts/GLM-5.2-Q4.base.part-000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc36eece6e94329331b5c4abe4f0d31c06d56658c4360ebb1c4b8a974ed20bfe
3
+ size 48318382080
parts/GLM-5.2-Q4.base.part-001 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972a00408ed3425f7fcda9a4c0abb3832f16b8a7d1edd7ffe19257dda5b5d93a
3
+ size 48318382080
parts/GLM-5.2-Q4.base.part-002 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d571452d9c244d119afea132bcab079a4062e3488476ea8bb3e19886b351d7c9
3
+ size 48318382080
parts/GLM-5.2-Q4.base.part-003 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b718dddde117800fde1d396a27b3370a0788ce8c801854d413548e18bdbdb0a
3
+ size 48318382080
parts/GLM-5.2-Q4.base.part-004 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a41af4d089a179bdb9779620cfe1a35220e4cec71050fd9b74f039ee1a2586c9
3
+ size 48318382080
parts/GLM-5.2-Q4.base.part-005 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33ec8cce84b0897825c2bbb5f5bbdbd7f527c1fef531a183fa6747912645a39d
3
+ size 48318382080
parts/GLM-5.2-Q4.base.part-006 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1616e06745b92417ecf7f23a32a3c887de71f3dfe066cc4ecf6ae6f08933281
3
+ size 48318382080
parts/GLM-5.2-Q4.base.part-007 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a45546c8c6e0942a8228001dcb2cd7cac92a8f5bff74aae0e11513f25926c2c6
3
+ size 48318382080
parts/GLM-5.2-Q4.base.part-008 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5931c5abbfc3743b052e90971d73d7f0010e000d9cd9fe224a0a6e55dcb16139
3
+ size 45377355776