ð touch grass
Nina Beerbower
nbeerbower
AI & ML interests
QLoRA finetuning and merging LLMs for fun. Also learning about diffusion and VLMs! (Out of space, won't be posting here anymore)
Recent Activity
updated a dataset about 3 hours ago
yotisstudios/RaifuWars-Warrior-SFT-v2 updated a model about 5 hours ago
schneewolflabs/Vernunft-Qwen3.6-27B-LoRA published a model about 5 hours ago
schneewolflabs/Vernunft-Qwen3.6-27B-LoRAOrganizations
model usecase
1
#1 opened 7 days ago
by 
ghit72
Prose? ðŠķ
3
#1 opened 10 days ago
by 
McG-221
Grand Wichtel
ðâĪïļ 1
2
#1 opened 11 days ago
by 
nightmedia
Decoding speed ?
1
#1 opened 16 days ago
by 
AliceThirty
Question about your Gutenberg preference tuning process
2
#1 opened 29 days ago
by 
AustinAligned
question abt training process
ð 1
4
#3 opened about 1 month ago
by 
Fizzarolli
26B?
5
#2 opened about 2 months ago
by 
FrenzyBiscuit
Qwen3.5 quantization sensitivity
2
#3 opened 3 months ago
by 
Mystique728
Please add preprocessor_config.json
ð 1
1
#1 opened 4 months ago
by 
darkneighbor667
Would be curious to see you do the 27B version
ð 1
1
#2 opened 5 months ago
by 
BigBeavis
What is this for?
1
#1 opened 5 months ago
by 
jimzlf
question
2
#1 opened 6 months ago
by 
Akicou
example workflow?
1
#1 opened 7 months ago
by 
Safeswimming69
Realistic images?
2
#1 opened 10 months ago
by 
olivetty
Any plans for future Qwen3 8B models?
ð 1
10
#2 opened about 1 year ago
by 
lemon07r
Dataset improvements for thinker LLM
1
#3 opened about 1 year ago
by 
Disya
Tranining syntax specifics.
2
#2 opened about 1 year ago
by 
Downtown-Case
Possibly the best Qwen2.5-32B tune?
âĪïļ 1
4
#1 opened about 1 year ago
by 
MetaphoricalCode
Gutenberg Vitus vs Encore
2
#1 opened about 1 year ago
by 
EloyOn
What is the chat template for koboldcpp?
1
#1 opened about 1 year ago
by 
FrescoHF