wzgrx
wzgrx
AI & ML interests
None yet
Recent Activity
new activity 6 days ago
huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:Great work liked a model 6 days ago
huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUFOrganizations
None yet
MTP head weights corrupted by abliteration: --spec-type draft-mtp yields 0% acceptance
1
#4 opened 6 days ago
by
wzgrx
Great work
🚀 6
#1 opened 6 days ago
by
wzgrx
发一个GUFF格式的
3
#1 opened 7 days ago
by
kelei999999
It is inferior to the qwen3.6 35 model in image and video recognition
4
#69 opened 8 days ago
by
wzgrx
I can't wait for the full version.
👀 4
19
#15 opened 5 months ago
by
thiagoakhe
The output of the pockerpal Android client is garbled, but it works normally with the old version
#20 opened 5 months ago
by
wzgrx
Is this based on the final quantization optimization version of unsloth?
3
#17 opened 5 months ago
by
wzgrx
Very good model. Request for support for models with more specifications.
👍 3
7
#1 opened 6 months ago
by
wzgrx
Request: Heretic version of Qwen3.5-9B
7
#3 opened 6 months ago
by
Nuke1229
Qwen3.5-27B?
1
#4 opened 6 months ago
by
wzgrx
Is there a workflow for nodes that load multiple LoRa modules? Thank you.
#15 opened 7 months ago
by
wzgrx
为什么controlnet全部失败
2
#23 opened 7 months ago
by
TJundx
Which version should I choose between bf and fb? Device 5090, pursuit of speed
#8 opened about 1 year ago
by
wzgrx
Can I train LoRa based on this model? Are there any relevant tutorials and training parameters?
3
#25 opened over 1 year ago
by
wzgrx
FileNotFoundError: [WinError 2]
1
#1 opened over 1 year ago
by
wzgrx
xformers-windows-torch2.8-cu128-py311 please
2
#1 opened over 1 year ago
by
wzgrx
Why is the graphics memory requirement of SDxl 1.0 so high? Starting at 12GB, can't you use anything below 12GB?
👍 2
3
#13 opened about 3 years ago
by
wzgrx