Kooten
Kooten
AI & ML interests
AI lobotomy
Recent Activity
new activity 7 days ago
Kooten/gemma-4-31b-abliterated-v1.1:KL Div updated a model 7 days ago
Kooten/gemma-4-31b-abliterated-v1.1-GGUF published a model 7 days ago
Kooten/gemma-4-31b-abliterated-v1.1-GGUFOrganizations
None yet
KL Div
3
#1 opened 7 days ago
by
SerialKicked
Issue with model.safetensors.index.json
2
#1 opened over 1 year ago
by
ghostlamp
Getting a ValueError upon loading the model, tensors are not matching.
3
#1 opened over 1 year ago
by
johann15
Help. Getting Gibberish Responses?
6
#1 opened about 2 years ago
by deleted
Request for Higher 4bpw Quant
3
#1 opened about 2 years ago
by deleted
Any plan of realeasing q2_k_s quants?
4
#1 opened about 2 years ago
by
stduhpf
can i request 8bpw?
1
#1 opened about 2 years ago
by
Perpetuity7
Thanks man!
❤️ 1
10
#1 opened about 2 years ago
by
Nexesenex
Thank you so much for doing this chore. IQ2 > EXL2 @ <3bpw ?
❤️ 1
1
#2 opened about 2 years ago
by
ProphetOfBostrom
More quant?
2
#1 opened about 2 years ago
by
Kotokin
Request for another exl quant
2
#1 opened about 2 years ago
by
Clevyby
It Delivers!
❤️ 1
2
#1 opened about 2 years ago
by
LunarAura
using context above 4096 - need to set compress_pos_emb above 1?
5
#1 opened over 2 years ago
by
Samvanity
Kobold can run IQ2
2
#1 opened about 2 years ago
by
Nexesenex
This is the other model that had the same problem to my knowledge.
2
#1 opened about 2 years ago
by
Nitral-AI
Thanks my dude <3
3
#1 opened about 2 years ago
by
Nitral-AI
VRAM usage & card recommendations
1
#1 opened over 2 years ago
by
tensiondriven
Thanks! I like this one :-)
1
#1 opened over 2 years ago
by
ThiloteE
exllama version?
2
#1 opened over 2 years ago
by
Nexesenex