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 5 days ago
Gryphe/Gemma-4-26B-A4B-StyleTune-V2:QAT versions please 🙏 liked a model 8 days ago
unsloth/gemma-4-26B-A4B-it-qat-GGUF liked a model about 1 month ago
google/gemma-4-31B-itOrganizations
QAT versions please 🙏
👍 2
3
#2 opened 5 days ago
by 
Iwaku-Real
Accessing the weights
#2 opened about 2 months ago
by s1arsky
New activity in groxaxo/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-heretic-EXL3-6bpw 3 months ago
Interest in 4bpw
❤️ 2
1
#1 opened 4 months ago
by 
19440harry
Request for access / IQ4_XS imatrix quantization
2
#3 opened 3 months ago
by s1arsky
Hallucinations resistance ?
🔥 1
3
#3 opened 3 months ago
by s1arsky
Links to GGUF models in the model description doesn' work.
3
#1 opened 3 months ago
by s1arsky
Broken output on koboldcpp
3
#1 opened 3 months ago
by 
Dzondo58
Use --reasoning-budget 0 for instruct mode
🚀👍 2
3
#5 opened 4 months ago
by 
vico44
YanLabs/gemma-3-27b-it-abliterated-normpreserve (EXL3_4.5bpw)
#27 opened 6 months ago
by s1arsky
FlareRebellion/BereavedCompound-v1.0-24b
➕ 1
1
#21 opened 6 months ago
by s1arsky
Eval request - Casual-Autopsy/Maginum-Cydoms-24B
#485 opened 6 months ago
by s1arsky
Please Eval - TheDrummer/Cydonia-24B-v4.3
#480 opened 6 months ago
by s1arsky
Eval request - GLM 4.6V
#474 opened 7 months ago
by s1arsky
Request for a different model
4
#1 opened 7 months ago
by 
ggnoy
UGI Leaderboard Writin benchmark
4
#2 opened 9 months ago
by s1arsky
Eval request - ReadyArt/4.2.0-Broken-Tutu-24b
#409 opened 8 months ago
by s1arsky
Eval Request - FlareRebellion/WeirdCompound-v1.7-24b
#399 opened 9 months ago
by s1arsky
Q6/Q8?
#1 opened 9 months ago
by 
sphiratrioth666