wenhua cheng

wenhuach's activity

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

New activity in Intel/GLM-5-int4-mixed-AutoRound about 8 hours ago

This model always predicts some few nonsense sequences

5

#1 opened 13 days ago by

CharlesChen2023

liked a model 1 day ago

Intel/Step-3.5-Flash-int4-mixed-AutoRound

Text Generation • 28B • Updated 1 day ago • 114 • 5

New activity in Intel/Qwen3.5-122B-A10B-int4-AutoRound 2 days ago

Does the A100 work?

6

#1 opened 14 days ago by

xz123321

New activity in Intel/Qwen3.5-35B-A3B-int4-AutoRound 9 days ago

Thanks! And MTP key question

9

#1 opened 10 days ago by

seanthomaswilliams

New activity in Intel/GLM-5-int4-mixed-AutoRound 10 days ago

vLLM fails to serve Intel/GLM-5-int4-mixed-AutoRound on NVIDIA DGX Spark (GB10, sm121) due to no valid MLA attention backend (qk_nope_head_dim 192)

1

#2 opened 10 days ago by

oliverjohnwilson

liked a model 10 days ago

kaitchup/Qwen3.5-27B-autoround-W4A16

7B • Updated 14 days ago • 2.12k • 8

updated 4 models 13 days ago

Intel/Qwen3.5-122B-A10B-int4-AutoRound

20B • Updated about 4 hours ago • 39.1k • 15

Intel/GLM-5-int4-mixed-AutoRound

117B • Updated 13 days ago • 2.85k • 2

Intel/Qwen3.5-397B-A17B-int4-AutoRound

Updated 13 days ago • 11.5k • 9

Intel/Qwen3.5-35B-A3B-int4-AutoRound

6B • Updated about 2 hours ago • 9.78k • 21

liked 3 models 14 days ago

Intel/Qwen3.5-122B-A10B-int4-AutoRound

20B • Updated about 4 hours ago • 39.1k • 15

Intel/Qwen3.5-35B-A3B-int4-AutoRound

6B • Updated about 2 hours ago • 9.78k • 21

Intel/Qwen3.5-397B-A17B-int4-AutoRound

Updated 13 days ago • 11.5k • 9

published a model 14 days ago

Intel/Qwen3.5-35B-A3B-int4-AutoRound

6B • Updated about 2 hours ago • 9.78k • 21

published a model 16 days ago

Intel/GLM-5-int4-mixed-AutoRound

117B • Updated 13 days ago • 2.85k • 2

New activity in Intel/GLM-4.7-Flash-int4-AutoRound 20 days ago

Convert to gguf-q2ks-mixed-AutoRound?

🔥 2

4

#2 opened about 2 months ago by

limcheekin

New activity in Intel/Qwen3-Next-80B-A3B-Thinking-int4-AutoRound about 1 month ago

Qwen/Qwen3-Next-80B-A3B-Thinking has MMLU_PRO 82.7 but you guys get 0.7271

3

#2 opened 6 months ago by

hlxxxxxx

updated 2 models about 2 months ago

Intel/DeepSeek-V3.2-int4-AutoRound

Text Generation • 3B • Updated Jan 23 • 563 • 2

Intel/GLM-4.7-Flash-int4-AutoRound

1B • Updated Jan 22 • 2.33k • 8

published a model about 2 months ago

Intel/GLM-4.7-Flash-int4-AutoRound

1B • Updated Jan 22 • 2.33k • 8