Evil Person
evilperson068
·
AI & ML interests
None yet
Recent Activity
new activity 27 days ago
Viggle/Viggle-Animate:Comparing with vanilla H3 Ref2Video model? new activity about 2 months ago
Qwen/Qwen3.8-27B-FP8:RTX Pro 6000 @ 23 tokens/s new activity about 2 months ago
meta-models/Muse-Glimmer-30B:Anyone tried? How do you think?Organizations
None yet
Comparing with vanilla H3 Ref2Video model?
5
#1 opened 28 days ago
by
evilperson068
RTX Pro 6000 @ 23 tokens/s
12
#9 opened about 2 months ago
by
evilperson068
Anyone tried? How do you think?
3
#13 opened about 2 months ago
by
evilperson068
Not thinking even when `chat_template_kwargs` is set?
👍 3
10
#13 opened 2 months ago
by
evilperson068
Overtraining
4
#3 opened 4 months ago
by
DodoPapa
This is Awesome!
❤️ 2
#1 opened 4 months ago
by
evilperson068
CUDA Error
#4 opened 5 months ago
by
evilperson068
Avg Draft acceptance rate is low.
17
#2 opened 5 months ago
by
fouvy
vllm crashing on 0.19.0
2
#38 opened 6 months ago
by
evilperson068
Garbage output from transcribe method
10
#28 opened 6 months ago
by
svennslu
这个模型可以同时通过洗车店和学校大扫除测试,很厉害。
5
#14 opened 6 months ago
by
AliBB64
THANK YOU MiniMax Team for Keeping Your Promise
🔥 2
3
#11 opened 6 months ago
by
evilperson068
Best birthday gift ever.
🤗🚀 6
4
#3 opened 6 months ago
by
Darkknight535
Possible to run on single RTX Pro 6000 (96GB VRAM)?
#2 opened 7 months ago
by
evilperson068
Thank You! RedNote Team!
🔥 1
1
#8 opened 7 months ago
by
evilperson068
[WORKING] Enable Reasoning/Thinking for Qwen3-Coder-Next
❤️👍 6
#34 opened 8 months ago
by
evilperson068
Quality Degredation?
#2 opened 8 months ago
by
evilperson068
Best Practice for Z-Image Base vs Turbo LoRA Training and Generation
9
#18 opened 8 months ago
by
YOUARECOOL
Endless Repetition? Anyone encountered?
5
#48 opened 8 months ago
by
evilperson068
[Question] Why Training Adapter
7
#1 opened 10 months ago
by
evilperson068