Do you have a paper documenting what "MRI" means?
Tom
TomLucidor
AI & ML interests
None yet
Recent Activity
new activity 10 days ago
inclusionAI/Ring-2.6-1T:Ring Mini / Ring Flash (either Linear or Sparse models)? new activity 23 days ago
z-lab/gemma-4-26B-A4B-it-DFlash:This works with a quantsized version?Organizations
Ring Mini / Ring Flash (either Linear or Sparse models)?
2
#1 opened 17 days ago
by TomLucidor
This works with a quantsized version?
2
#4 opened 26 days ago
by 
khronnuz
Acceptance rate drop in non-thinking scenarios
👍 1
1
#7 opened about 1 month ago
by 
lillilyh
DFlash compatibility with AutoRound (W4A16) quantized Qwen3.5-9B in vLLM?
2
#1 opened 2 months ago
by 
Vishva007
Is have Qwen3.6 35B A3B FP8 version?
➕ 1
2
#4 opened about 1 month ago
by 
whaozl
Qwen3.5 2B/0.5B
1
#1 opened about 2 months ago
by 
packetsent
30+ Billion Models?
🚀 3
1
#2 opened about 1 month ago
by 
bobbytaylor
Will there be Mini/Nano models as well?
#2 opened about 1 month ago
by TomLucidor
replied to SeaWolf-AI's post about 2 months ago
Open-weights only toggle for Web UI
👍 1
#4 opened 2 months ago
by TomLucidor
Sort by Pass@5 % on web UI
👍 1
#3 opened 2 months ago
by TomLucidor
Can you add in Qwen3.5 and other series of models for testing?
3
#2 opened 2 months ago
by TomLucidor
Some questions on BitNet PTQ
2
#1 opened 4 months ago
by TomLucidor
Will there be a base model?
2
#4 opened 4 months ago
by 
zianglih
Has REAM been checked for their resilience towards quantization?
4
#1 opened 4 months ago
by TomLucidor
How is this different from the other quants?
8
#1 opened 3 months ago
by TomLucidor
Will Hybrid Attention RP models get some love?
➕ 1
#7 opened 3 months ago
by TomLucidor
ValueError: Model type lfm2_moe not supported.
5
#1 opened 8 months ago
by 
kadirnar
replied to SeaWolf-AI's post 3 months ago
Could you see if SLMs (models with <80B, <48B, <36B, <20B, etc.) also having this meta-cognitive power?