HELVETE-X
🌍
20
Chat with an unrestricted AI model
VORTEX
Abhaykoul
VAIBHAV22334455's profile picture
DualityAI-RebekahBogdanoff's profile picture
21world's profile picture
·
AI & ML interests
None yet
Recent Activity
updated
a Space
3 days ago
Abhaykoul/HELVETE-X
new activity
3 days ago
Abhaykoul/HELVETE-X:Update README.md
liked
a model
4 days ago
HelpingAI/Dhanishtha-2.0-0126
Organizations
updated
a
Space
3 days ago
Update README.md
#1 opened 3 days ago
by
ash1102
liked
a
model
4 days ago
reacted to
AIPreplabs's
post with 🔥
7 days ago
Post
2304
We’ve all had that moment where we watch a tutorial, nod along, but then realize we can’t actually do it ourselves because watching is just passive. At AIPrep, we are fixing this "watch and forget" cycle by building a foundational Generative Explanatory Model (GEM). GEM doesn't just give you a video or a wall of text; it builds an interactive lesson that asks you questions, catches your mistakes in real time, and adapts to your pace. We have just finished preparing our specialized datasets for this interactive logic, and you can already check them out on our profile to see how we are structuring this step-by-step reasoning. Training for the foundational model starts very soon, so stay in touch because something revolutionary is coming to the world of AI education. You can see our progress at aiprep.in.
- 2 replies
upvoted
2
changelogs
13 days ago
Changelog
Sort Datasets by Size
•
82
Changelog
View Running Jobs Count from the User Menu
•
44
Is UnfilteredAI dead now?
1
#3 opened 15 days ago
by
Abhaykoul
updated
a
collection
16 days ago
updated
a
Space
23 days ago
published
a
Space
23 days ago
updated
a
model
27 days ago
published
a
model
27 days ago
Let's Talk about AI
91
#1 opened 6 months ago
by
kalashshah19
reacted to
KingNish's
post with 🔥
2 months ago
Post
2792
Muon vs MuonClip vs Muon+Adamw
Muon has gone from an experiment to a mainstream optimizer, but does it hold up for fine‑tuning? We ran head‑to‑head tests on Qwen3‑4B (10k+ high‑quality instruction rows) to find out.
Short story: Pure Muon converged fastest at the start, but its gradient‑norm spikes made training unstable. MuonClip (Kimi K2’s clipping) stabilizes long pretraining runs, yet in our small‑scale fine‑tune 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 Muon’s 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 fine‑tuning? We ran head‑to‑head tests on Qwen3‑4B (10k+ high‑quality instruction rows) to find out.
Short story: Pure Muon converged fastest at the start, but its gradient‑norm spikes made training unstable. MuonClip (Kimi K2’s clipping) stabilizes long pretraining runs, yet in our small‑scale fine‑tune 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 Muon’s spikes become catastrophic or if clipping wins out.
Full Blog Link: https://huggingface.co/blog/KingNish/optimizer-part1
reacted to
KingNish's
post with 🔥
2 months ago
Post
2619
I tested Muon vs MuonClip vs Muon+AdamW for fine-tuning LLMs
Just published a blog on that, Read here 👉 https://huggingface.co/blog/KingNish/optimizer-part1
Just published a blog on that, Read here 👉 https://huggingface.co/blog/KingNish/optimizer-part1
- 1 reply
upvoted
an
article
2 months ago
Article
Muon vs MuonClip vs Muon+AdamW for Fine-Tuning
•
14
liked
a
dataset
2 months ago
liked
a
model
2 months ago
