ZINWIN(Zuojun-Ye)
win10
AI & ML interests
I constructed a large number of novel model merging algorithms and developed a general SVD distillation method.
Recent Activity
liked a model about 7 hours ago
Lazarus-Ai/ReAligned-Qwen3.5-35B-A3B liked a model 2 days ago
google/gemma-4-12B-it liked a model 3 days ago
OpenMOSS-Team/MOSS-TTS-v1.5Organizations
google/gemma-4-31B-it-assistant
1
#2 opened 29 days ago
by win10
Request quantization to FP8
1
#1 opened about 1 month ago
by win10
表達感謝:部分思維鏈過長, 但使用此資料集訓練的模型很有個性
#17 opened about 1 month ago
by win10
[Question] Can the model be run on Nvidia DGX Spark?
2
#2 opened about 1 month ago
by 
hubertshelley
請問訓練方法是什麼?
#2 opened about 1 month ago
by win10
Has anyone successfully run it on two GB10 machines?
👍 1
3
#3 opened about 2 months ago
by win10
Step-3.5-Flash-mxfp4?
#2 opened about 2 months ago
by win10
Comfyui error
3
#3 opened 2 months ago
by win10
New activity in DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking 3 months ago
Please try out the template I provided; it can best mimic Claude's way of thinking.
3
#5 opened 3 months ago
by win10
win10/SVD-Qwen3-Coder-Next-Thinking
5
#6 opened 4 months ago
by win10
請求80B參數量的Qwen3.5
👀 1
1
#32 opened 4 months ago
by win10
request win10/SVD-Qwen3-Coder-Next-Thinking
#2 opened 4 months ago
by win10
Could you provide the official NVFP4 version? Dear friend.
#2 opened 4 months ago
by win10
Could you provide the official NVFP4 version? Dear friend.
1
#6 opened 4 months ago
by win10
Could we try quantizing it to fp8?
#1 opened 4 months ago
by win10
Could you try quantifying this model?
1
#1 opened 4 months ago
by win10