Shaun Prince
Suparious
AI & ML interests
Censorship deletion, Self-Hosting, Open Source models, inference engines, systems architecture, infrastructure.
Organizations
Where are the model cards?
1
#2 opened 4 months ago
by
Suparious
Performed my own Quantization, now encounter an error while running inference with vllm.
1
#1 opened 6 months ago
by
ryan-rozanitis-bd
float16 when
1
#4 opened 8 months ago
by
Pinguin
Llama-3-8B-Stroganoff-4.0
👍
1
1
#1 opened about 1 year ago
by
djuna
Whether Chinese is supported
2
#11 opened about 1 year ago
by
MagicSquash
Possibly the provided prompt format is wrong.
🧠
👍
6
12
#1 opened about 1 year ago
by
vevi33
no tokenizer.json?
2
#1 opened over 1 year ago
by
Suparious
Where are the model weights?
2
#1 opened over 1 year ago
by
Suparious
No tokenizer?
2
#1 opened over 1 year ago
by
Suparious
Failed to quantize
5
#1 opened over 1 year ago
by
Suparious
unable to make an AWQ quant
2
#1 opened over 1 year ago
by
Suparious
Very glitchy model.
8
#16 opened over 1 year ago
by
Guljaca
20K context on this AWQ
9
#1 opened over 1 year ago
by
djuna
dolphin-2.9.4-llama3.1-8b ?
32
#1 opened over 1 year ago
by
vaclavkosar
AWQ working for minitron
3
#1 opened over 1 year ago
by
Suparious
dolphin-2.9.4-llama3.1-8b ?
32
#1 opened over 1 year ago
by
vaclavkosar
dolphin-2.9.4-llama3.1-8b ?
32
#1 opened over 1 year ago
by
vaclavkosar