Hang Yin

h4x3rotab's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model about 4 hours ago

PhalaCloud/GLM-5.3-W4AFP8

Text Generation • 386B • Updated about 4 hours ago • 148 • 6

liked a model about 5 hours ago

PhalaCloud/GLM-5.3-W4AFP8

Text Generation • 386B • Updated about 4 hours ago • 148 • 6

New activity in PhalaCloud/GLM-5.2-W4AFP8 1 day ago

W4AFP8 for 5.3

6

#7 opened 14 days ago by

jlondon

published a model 2 days ago

PhalaCloud/GLM-5.3-W4AFP8

Text Generation • 386B • Updated about 4 hours ago • 148 • 6

updated a model about 1 month ago

PhalaCloud/GLM-5.2-W4A8-CT

Text Generation • 116B • Updated Jul 22 • 57

published a model about 1 month ago

PhalaCloud/GLM-5.2-W4A8-CT

Text Generation • 116B • Updated Jul 22 • 57

updated a model about 1 month ago

PhalaCloud/GLM-5.2-W4AFP8

Text Generation • 392B • Updated Jul 21 • 35.8k • 46

New activity in PhalaCloud/GLM-5.2-W4AFP8 about 2 months ago

ERROR: Should have a `model_type` key in its config.json

1

#5 opened 2 months ago by

PakJoeng

8xH20 141GB cuda out of memory

1

#6 opened 2 months ago by

ErisLU

New activity in PhalaCloud/GLM-5.2-W4AFP8 2 months ago

Any chances for A100?

1

#4 opened 2 months ago by

traphix

GLM-5.2-W4AFP8 on 8×H100: fp8_e4m3 KV cache produces corrupted output, while BF16 KV works correctly

1

#3 opened 2 months ago by

loveblairsky

Is the quantize script opensource?

3

#2 opened 2 months ago by

wxsm

KTransformers + SGLang

1

#1 opened 2 months ago by

mtcl

liked a model 2 months ago

PhalaCloud/GLM-5.2-W4AFP8

Text Generation • 392B • Updated Jul 21 • 35.8k • 46

published a model 2 months ago

PhalaCloud/GLM-5.2-W4AFP8

Text Generation • 392B • Updated Jul 21 • 35.8k • 46

liked a dataset 4 months ago

legalcitebench/LegalCiteBench

Preview • Updated May 6 • 80 • 1