s1arsky
s1arsky
AI & ML interests
I create datasets for fine tuning base->adventure/RP open models. Also, on occasion I fill gaps with quants for choosen ERP/RP model.
Recent Activity
new activity 1 day ago
turboderp/Qwen3.8-27B-exl3:model_of_choice new activity 4 days ago
turboderp/Huihui-Qwen3.8-27B-abliterated-exl3:thumbs upOrganizations
model_of_choice
👀 1
6
#8 opened 22 days ago
by s1arsky
thumbs up
➕ 1
#1 opened 4 days ago
by s1arsky
Field manual to setting up local inference for exl3 quant model.
#11 opened 7 days ago
by s1arsky
3.05 HumanEval
👍🔥 3
8
#6 opened 13 days ago
by 
johnlakness
4bpw work on my 3090 + 64 RAM - excellence.
❤️👍 11
22
#2 opened 18 days ago
by s1arsky
UD_Q4_XL benchmarks ?
1
#1 opened 18 days ago
by s1arsky
context type MTP requested but model doesn't contain MTP layers
👀 4
6
#47 opened 20 days ago
by 
Manhandle6292
My findings for this setup.
🚀 2
1
#1 opened 28 days ago
by s1arsky
Keeps getting stuck in thinking loops
👍 7
3
#12 opened 3 months ago
by 
jpschroeder
QAT versions please 🙏
👍 13
3
#2 opened 3 months ago
by 
Iwaku-Real
Accessing the weights
#2 opened 5 months ago
by s1arsky
New activity in groxaxo/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-heretic-EXL3-6bpw 5 months ago
Interest in 4bpw
❤️ 2
1
#1 opened 6 months ago
by 
19440harry
Request for access / IQ4_XS imatrix quantization
2
#3 opened 5 months ago
by s1arsky
Hallucinations resistance ?
🔥 1
3
#3 opened 5 months ago
by s1arsky
Links to GGUF models in the model description doesn' work.
3
#1 opened 6 months ago
by s1arsky
Broken output on koboldcpp
3
#1 opened 6 months ago
by 
Dzondo58
Use --reasoning-budget 0 for instruct mode
🚀👍 2
3
#5 opened 7 months ago
by 
vico44
YanLabs/gemma-3-27b-it-abliterated-normpreserve (EXL3_4.5bpw)
#27 opened 8 months ago
by s1arsky