Shaun Prince
Suparious
AI & ML interests
Censorship deletion, Self-Hosting, Open Source models, inference engines, systems architecture, infrastructure.
Recent Activity
updated
a model
about 23 hours ago
Suparious/FLUX.1-Redux-dev-adaptor-bfl
updated
a model
about 23 hours ago
Suparious/FP-image-to-video-FLUX.1-HV-bf16
published
a model
1 day ago
Suparious/FP-image-to-video-FLUX.1-HV-bf16
Organizations
Suparious's activity
float16 when
1
#4 opened 3 days ago
by
Pinguin

Llama-3-8B-Stroganoff-4.0
1
1
#1 opened 7 months ago
by
djuna

Whether Chinese is supported
2
#11 opened 7 months ago
by
MagicSquash

Possibly the provided prompt format is wrong.
6
12
#1 opened 7 months ago
by
vevi33
no tokenizer.json?
2
#1 opened 8 months ago
by
Suparious

Where are the model weights?
2
#1 opened 8 months ago
by
Suparious

No tokenizer?
2
#1 opened 8 months ago
by
Suparious

Failed to quantize
5
#1 opened 8 months ago
by
Suparious

unable to make an AWQ quant
2
#1 opened 8 months ago
by
Suparious

Very glitchy model.
8
#16 opened 8 months ago
by
Guljaca
20K context on this AWQ
9
#1 opened 8 months ago
by
djuna

dolphin-2.9.4-llama3.1-8b ?
32
#1 opened 8 months ago
by
vaclavkosar

AWQ working for minitron
3
#1 opened 8 months ago
by
Suparious

Great work!
1
#3 opened 11 months ago
by
mclassHF2023
Update README.md with license information
#2 opened 10 months ago
by
Chen-01AI
Update README.md with license information
1
#2 opened 10 months ago
by
Chen-01AI
How to convert to HF format?
8
5
#6 opened 11 months ago
by
ddh0

Suggestion
6
#3 opened 11 months ago
by
KingNish

FP16 vs BF16
16
#2 opened 12 months ago
by
Virt-io
fp16 model?
12
#2 opened about 1 year ago
by
nonetrix
