NSFW - Text to Image
Collection
Uncensored Text to image models
â˘
5 items
â˘
Updated
AI & ML interests
None defined yet.
Recent Activity
XetroÂ
updated
2
collections
about 3 hours ago
Is UnfilteredAI dead now?
1
#3 opened about 14 hours ago
by
Abhaykoul
Post
2631
Muon vs MuonClip vs Muon+Adamw
Muon has gone from an experiment to a mainstream optimizer, but does it hold up for fineâtuning? We ran headâtoâhead tests on Qwen3â4B (10k+ highâquality instruction rows) to find out.
Short story: Pure Muon converged fastest at the start, but its gradientânorm spikes made training unstable. MuonClip (Kimi K2âs clipping) stabilizes long pretraining runs, yet in our smallâscale fineâtune it underperformed, lower token accuracy and slower convergence. The winner was the hybrid: Muon for 2D layers + AdamW for 1D layers. It delivered the best balance of stability and final performance and even beat vanilla AdamW.
Takeaway: for small-scale fine-tuning, hybrid = practical and reliable.
Next Step: scale to larger models/datasets to see if Muonâs spikes become catastrophic or if clipping wins out.
Full Blog Link: https://huggingface.co/blog/KingNish/optimizer-part1
Muon has gone from an experiment to a mainstream optimizer, but does it hold up for fineâtuning? We ran headâtoâhead tests on Qwen3â4B (10k+ highâquality instruction rows) to find out.
Short story: Pure Muon converged fastest at the start, but its gradientânorm spikes made training unstable. MuonClip (Kimi K2âs clipping) stabilizes long pretraining runs, yet in our smallâscale fineâtune it underperformed, lower token accuracy and slower convergence. The winner was the hybrid: Muon for 2D layers + AdamW for 1D layers. It delivered the best balance of stability and final performance and even beat vanilla AdamW.
Takeaway: for small-scale fine-tuning, hybrid = practical and reliable.
Next Step: scale to larger models/datasets to see if Muonâs spikes become catastrophic or if clipping wins out.
Full Blog Link: https://huggingface.co/blog/KingNish/optimizer-part1
Post
2573
I tested Muon vs MuonClip vs Muon+AdamW for fine-tuning LLMs
Just published a blog on that, Read here đ https://huggingface.co/blog/KingNish/optimizer-part1
Just published a blog on that, Read here đ https://huggingface.co/blog/KingNish/optimizer-part1
-
- 1 reply
AI Models with absolutely no boundaries or guardrails
4
#2 opened about 2 months ago
by
alanlj1956
Update README.md
#2 opened 3 months ago
by
Deathstormer
How to install this model to Ollama exactly
13
#2 opened over 1 year ago
by
codefacer
architecture
2
#7 opened 10 months ago
by
BornSaint