Big Beavis
BigBeavis
AI & ML interests
chat, roleplay
Recent Activity
liked a model 20 days ago
prithivMLmods/Gliese-Qwen3.5-27B-Abliterated-Caption new activity 22 days ago
nbeerbower/Qwen3.5-9B-Writing-DPO:Would be curious to see you do the 27B version new activity 24 days ago
ArliAI/Qwen3.5-27B-Derestricted:Still quite restricted for a "derestricted" claim.Organizations
None yet
Would be curious to see you do the 27B version
π 1
1
#2 opened 22 days ago
by
BigBeavis
Still quite restricted for a "derestricted" claim.
1
#2 opened 24 days ago
by
BigBeavis
Promising
β€οΈ 1
1
#1 opened 25 days ago
by
sophosympatheia
What's the point if the model spends most of its thinking budget analyzing the "safety" of the prompt?
π 1
2
#2 opened about 2 months ago
by
BigBeavis
Interesting experiment, but lacks stability and emotional intelligence
#1 opened about 2 months ago
by
BigBeavis
In roleplay context i find this release more consistent than the newer "refined" version...
1
#1 opened about 2 months ago
by
BigBeavis
Again about the IQ4_XS...
1
#1 opened 2 months ago
by
BigBeavis
That thing... your IQ4_XS quant... hand it over...
1
#2 opened 2 months ago
by
BigBeavis
Please add IQ4_XS gguf
#1 opened 2 months ago
by
BigBeavis
The model has severe grammar issues
1
#4 opened 3 months ago
by
BigBeavis
The model doesn't know about itself
2
#17 opened 5 months ago
by
sakazakiMGJ
Perhaps the most optimal model for 16GB GPU for long context.
β€οΈ 1
#4 opened 4 months ago
by
BigBeavis
The return of the king
π₯ 1
#1 opened 4 months ago
by
BigBeavis
What's the correct reasoning format?
5
#2 opened 5 months ago
by
BigBeavis
Why not experiment?
π 1
3
#1 opened 5 months ago
by
Dampfinchen
This is hands down the best iteration of GLM4 32B
3
#2 opened 5 months ago
by
BigBeavis
This vs the 24b version.
#5 opened 7 months ago
by
BigBeavis
Good model but too stubborn
2
#4 opened 7 months ago
by
Bhazo
Unexpected Three Body reference
2
#1 opened 9 months ago
by
BigBeavis