Olaf Kowalsky
Olafangensan
AI & ML interests
None yet
Recent Activity
new activity
about 1 month ago
bartowski/RekaAI_reka-flash-3-GGUF:REALLY slow with flash attention and quantized cache.
new activity
about 1 month ago
Undi95/QwQ-RP:This model is SUCH A TRYHARD
new activity
about 2 months ago
Qwen/QwQ-32B:recommended generation parameters
Organizations
None yet
Olafangensan's activity
REALLY slow with flash attention and quantized cache.
7
#2 opened about 1 month ago
by
Olafangensan
This model is SUCH A TRYHARD
2
3
#1 opened about 1 month ago
by
Olafangensan
recommended generation parameters
6
#5 opened about 2 months ago
by
erichartford

Long output issues
1
#1 opened 3 months ago
by
Olafangensan
Feedback
11
#1 opened 5 months ago
by
xxx777xxxASD

Better performance with ChatML for novel writing.
#6 opened 8 months ago
by
Olafangensan
Feedback
46
#1 opened 8 months ago
by
MarinaraSpaghetti

GGUF quants version?
1
2
#1 opened 8 months ago
by
celsowm

Feedback
14
#1 opened 9 months ago
by
MarinaraSpaghetti

eos_token_id error in oobabooga
6
#1 opened 9 months ago
by
Olafangensan
Wrong position embedding size?
1
#1 opened 9 months ago
by
lanking

Unexpected Behaviors
7
#1 opened 9 months ago
by
Olafangensan
KoboltCPP settings? Preset?
1
#2 opened 11 months ago
by
Olafangensan
Finally, an instruct fine tune!
1
#9 opened 11 months ago
by
Olafangensan
Yi 34b 200k context update, will there be an updated version of this one?
3
4
#9 opened about 1 year ago
by
Olafangensan
Make faster
2
#22 opened over 1 year ago
by
luklue