Hugging Face's logo

Grawnch
/
TokenWing-Model-Assets

GGUF
tokenwing
Mixture of Experts
Model card Files
xet
 Community
Grawnch commited on
Commit
ce08434
·
verified ·
1 Parent(s): a132c6b

Upload Ling 3.0 Flash and Flint 40B .correction, .vram-experts.json, and .layer-order.json assets

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. Ling-3.0-flash-MXFP4_MOE.correction +3 -0
  3. Ling-3.0-flash-MXFP4_MOE.experts.layer-order.json +1 -0
  4. Ling-3.0-flash-MXFP4_MOE.vram-experts.json +0 -0
  5. README.md +23 -0
  6. flint-UD-Q4_K_XL.correction +3 -0
  7. flint-UD-Q4_K_XL.experts.layer-order.json +1 -0
  8. flint-UD-Q4_K_XL.vram-experts.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
+ Ling-3.0-flash-MXFP4_MOE.correction filter=lfs diff=lfs merge=lfs -text
37
+ flint-UD-Q4_K_XL.correction filter=lfs diff=lfs merge=lfs -text
Ling-3.0-flash-MXFP4_MOE.correction ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11bb5bf0064a63b7357152eadb76717c89c1cfb9235311676dfae0d2daae06ed
3
+ size 372310016
Ling-3.0-flash-MXFP4_MOE.experts.layer-order.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"format":"tokenwing layer order v1","arch":"bailingmoe3","order":[2,3,4,5,17,6,18,15,9,11,10,16,7,12,8,14,13,27,41,28,30,26,25,40,21,19,29,33,31,24,23,22,20,32,39,34,35,37,36,38]}
Ling-3.0-flash-MXFP4_MOE.vram-experts.json ADDED
The diff for this file is too large to render. See raw diff
 
README.md ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - tokenwing
4
+ - moe
5
+ - gguf
6
+ ---
7
+
8
+ # TokenWing Model Assets (`Ling 3.0 Flash` & `Flint 40B`)
9
+
10
+ Pre-computed `.correction`, `.vram-experts.json`, and `.experts.layer-order.json` companion files for:
11
+ - `runmyai/Ling-3.0-Flash-TokenWing` (`Ling-3.0-flash-MXFP4_MOE.*`)
12
+ - `runmyai/Flint-40B-TokenWing` (`flint-UD-Q4_K_XL.*`)
13
+
14
+ ## Files & SHA-256 Checksums
15
+
16
+ | File | Model | Size (Bytes) | SHA-256 |
17
+ | :--- | :--- | ---: | :--- |
18
+ | `Ling-3.0-flash-MXFP4_MOE.correction` | Ling 3.0 Flash | `372,310,016` | `11bb5bf0064a63b7357152eadb76717c89c1cfb9235311676dfae0d2daae06ed` |
19
+ | `Ling-3.0-flash-MXFP4_MOE.vram-experts.json` | Ling 3.0 Flash | `408,021` | `68a510e131f6e04b188a0d198d8c2e9d9d4522015fb3c153d38abb1753d2e0b2` |
20
+ | `Ling-3.0-flash-MXFP4_MOE.experts.layer-order.json` | Ling 3.0 Flash | `180` | `65d65266e1ea4c0c799125da383ef9370b075b61ee77c406ced5fbf6fa0598ab` |
21
+ | `flint-UD-Q4_K_XL.correction` | Flint 40B | `190,906,368` | `c1c955bdd7c2f0e1533559e5639a05ebad60afbb6c4e86ce9829091f3a801772` |
22
+ | `flint-UD-Q4_K_XL.vram-experts.json` | Flint 40B | `477,237` | `8e3ca18ccb936fc61db53cb2a543ee957e1704e0e4464f9b6f8d198d509ec39b` |
23
+ | `flint-UD-Q4_K_XL.experts.layer-order.json` | Flint 40B | `195` | `560b160f5316b8faea89dac810739216ca9a4feef9f8dd2d0cb759fed56aaf1e` |
flint-UD-Q4_K_XL.correction ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1c955bdd7c2f0e1533559e5639a05ebad60afbb6c4e86ce9829091f3a801772
3
+ size 190906368
flint-UD-Q4_K_XL.experts.layer-order.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"format":"tokenwing layer order v1","arch":"flint","order":[2,3,4,5,6,7,8,10,9,11,12,14,32,13,30,45,27,29,40,36,44,42,43,31,41,39,34,38,37,35,28,46,26,15,48,18,47,16,33,24,19,25,17,22,23,21,20]}
flint-UD-Q4_K_XL.vram-experts.json ADDED
The diff for this file is too large to render. See raw diff