Timon Käch
CyberTimon
AI & ML interests
ai text generation
Recent Activity
liked
a model
3 days ago
Qwen/Qwen2.5-Omni-3B
new activity
4 days ago
unsloth/Qwen3-30B-A3B-GGUF:`UD-Q4_K_XL` or `Q4_K_M`?
Organizations
CyberTimon's activity
Feedback: It's a good model, however it hallucinates very badly at local facts (Germany)
8
2
#12 opened 4 days ago
by
Dampfinchen
`UD-Q4_K_XL` or `Q4_K_M`?
9
#6 opened 4 days ago
by
pootow
Amazing, thank you so much. Small question :)
1
4
#2 opened 10 months ago
by
CyberTimon

GGUF Quants?
3
#1 opened 12 months ago
by
CyberTimon

What is 256k?
16
#1 opened about 1 year ago
by
supercharge19
Brain issues
8
#4 opened about 1 year ago
by
CyberTimon

I Guess I'll Be "That Guy"... SDXL?
7
#2 opened about 1 year ago
by
97Buckeye
We are working on creating a single 22b from this model
16
21
#5 opened about 1 year ago
by
rombodawg

Release weights of smaller Experimental MoE
7
2
#12 opened about 1 year ago
by
shahules786

Pattern
13
#3 opened about 1 year ago
by
tintwotin
Whats up with TheBloke ?
15
30
#2 opened about 1 year ago
by
Languido
Not working
3
#2 opened over 1 year ago
by
PeepDaSlan9

Quants
7
#1 opened over 1 year ago
by
CyberTimon

Hallucinations
2
10
#2 opened over 1 year ago
by
Ricepig

Fix Stop Tokens
2
#2 opened over 1 year ago
by
CyberTimon

Exciting, how can you do that so quickly?
5
#1 opened over 1 year ago
by
KnutJaegersberg

It would be useful if someone spent the time to convert the tokenizer to gpt2 HF format
2
#9 opened over 1 year ago
by
KnutJaegersberg

Training dataset + Hyperparamters
2
2
#1 opened over 1 year ago
by
Viewegger
Support for swiss german - please!
1
#15 opened over 1 year ago
by
CyberTimon

tokenizer.model
1
6
#6 opened over 1 year ago
by
nds90