Lockout
Lockout
AI & ML interests
None yet
Recent Activity
updated a model 2 days ago
Lockout/krea2-comfy-int4-mixed published a model 2 days ago
Lockout/krea2-comfy-int4-mixed new activity about 1 month ago
bertbobson/Ideogram-4-INT8-ConvRot:Do we still turn on convrot on these?Organizations
None yet
Do we still turn on convrot on these?
4
#2 opened about 1 month ago
by
Lockout
System prompt claims vision capabilities, but no vision encoder weights are included
4
#22 opened 5 months ago
by
T0mSIlver
For anyone who finds this
#1 opened 2 months ago
by
Lockout
q8_0 mmproj?
1
#8 opened 2 months ago
by
Lockout
mmproj are undersized
#1 opened 2 months ago
by
Lockout
Heads Up (May 1): Transformers Config Fix – What It Means for GGUFs & Quantized & Fine-Tuned Models
👍🔥 14
8
#18 opened 3 months ago
by
juliendenize
Finally dense 100b+!
🔥❤️ 5
12
#6 opened 3 months ago
by
Sliderpro93
GGUF/llama.cpp support
🔥 1
3
#1 opened 4 months ago
by
tcpmux
Thanks for the trim pointer but it needs one more place.
#2 opened 4 months ago
by
Lockout
How is it compared to the previous version?
2
#1 opened 4 months ago
by
Lockout
Love the license, confused by some of the decisions.
🤝👍 16
15
#15 opened 4 months ago
by
CyborgPaloma
does this contain actual lean
6
#4 opened 4 months ago
by
unokayish182
Devstral?
3
#1 opened 5 months ago
by
Lockout
Decent PPL with 100% IQ4_KSS
🔥 1
12
#3 opened 7 months ago
by
sokann
Its actually good model.
#1 opened 6 months ago
by
Lockout
The best model in the world for 5 months already
🔥 1
1
#4 opened 7 months ago
by deleted
Optimized Quant between 3bpw and 3.5bpw
32
#1 opened 7 months ago
by
remichu
Eval: https://huggingface.co/QuixiAI/Ina-v11.1 70b
#494 opened 7 months ago
by
Lockout