aidendle94/GLM-5.2-Hybrid-FP8-MXFP4
425B • Updated • 151 • 2
AK
kil0rk
AI & ML interests
None yet
Recent Activity
liked a model about 13 hours ago
aidendle94/GLM-5.2-Hybrid-FP8-MXFP4 new activity 2 days ago
Motif-Technologies/Motif-3-Beta:Why not open source liked a model 6 days ago
thinkingmachines/InklingOrganizations
None yet
liked a
model about 13 hours ago
Why not open source
👀 2
5
#1 opened 2 days ago
by 
gogo8232
liked a
model 6 days ago
liked 2
models 16 days ago
liked a
model 20 days ago
liked a
model 29 days ago
liked 4
models about 1 month ago
madeby561/GLM-5.2-NVFP4-REAP-504B-term
Text Generation • 290B • Updated • 2.57k • 17
deadbydawn101/RavenX-OpenFable-Coderagent-gemma-4-12B-coder-fable5-composer-Soulinfused-Remastered-GGUF
Text Generation • 12B • Updated • 7.21k • 18
build-small-hackathon/OpenMythos
Text Generation • 27B • Updated • 1.03k • 30
InternScience/Agents-K1
Text Generation • 4B • Updated • 907 • • 29
liked 4
models about 2 months ago
reacted to SeaWolf-AI's post with ❤️ 2 months ago
Post
5436
🧬 Darwin Family: Zero Gradient Steps, GPQA Diamond 88.89%
How far can we push LLM reasoning *without* training?
Our team at VIDRAFT submitted this paper to Daily Papers yesterday, and it's
currently #3. Huge thanks to everyone who upvoted — sharing the core ideas below.
🔗 Paper: Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning (2605.14386)
🔗 arXiv: https://arxiv.org/abs/2605.14386
🔗 Model: FINAL-Bench/Darwin-28B-REASON
🔗 Model: FINAL-Bench/Darwin-28B-Opus
---
TL;DR
Darwin Family is a training-free evolutionary merging framework.
By recombining the weight spaces of existing LLM checkpoints — with zero
gradient-based training — it reaches frontier-level reasoning.
- 🏆 Darwin-28B-Opus: GPQA Diamond 88.89%
- 💸 Zero gradient steps — not a single B200 or H200 hour needed
- 🧬 Consistent gains across 4B → 35B scale
- 🔀 Cross-architecture breeding between Transformer and Mamba families
- 🔁 Stable recursive multi-generation evolution
#Three Core Mechanisms
① 14-dim Adaptive Merge Genome — fine-grained recombination at both
component level (Attention / FFN / MLP / LayerNorm / Embedding) and block
level, expanding the prior evolutionary-merge search space.
② MRI-Trust Fusion — we diagnose each layer's reasoning contribution
via an **MRI (Model Reasoning Importance)** signal and fuse it with
evolutionary search through a **learnable trust parameter**. Trust the
diagnostic too much and search collapses; ignore it and search becomes
inefficient — Darwin learns the balance from data.
③ Architecture Mapper — weight-space breeding across heterogeneous
families. Attention × SSM crossover actually works.
Why It Matters
> Diagnose latent capabilities already encoded in open checkpoints,
> and recombine them — no gradients required.
Replies and critiques welcome 🙌
How far can we push LLM reasoning *without* training?
Our team at VIDRAFT submitted this paper to Daily Papers yesterday, and it's
currently #3. Huge thanks to everyone who upvoted — sharing the core ideas below.
🔗 Paper: Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning (2605.14386)
🔗 arXiv: https://arxiv.org/abs/2605.14386
🔗 Model: FINAL-Bench/Darwin-28B-REASON
🔗 Model: FINAL-Bench/Darwin-28B-Opus
---
TL;DR
Darwin Family is a training-free evolutionary merging framework.
By recombining the weight spaces of existing LLM checkpoints — with zero
gradient-based training — it reaches frontier-level reasoning.
- 🏆 Darwin-28B-Opus: GPQA Diamond 88.89%
- 💸 Zero gradient steps — not a single B200 or H200 hour needed
- 🧬 Consistent gains across 4B → 35B scale
- 🔀 Cross-architecture breeding between Transformer and Mamba families
- 🔁 Stable recursive multi-generation evolution
#Three Core Mechanisms
① 14-dim Adaptive Merge Genome — fine-grained recombination at both
component level (Attention / FFN / MLP / LayerNorm / Embedding) and block
level, expanding the prior evolutionary-merge search space.
② MRI-Trust Fusion — we diagnose each layer's reasoning contribution
via an **MRI (Model Reasoning Importance)** signal and fuse it with
evolutionary search through a **learnable trust parameter**. Trust the
diagnostic too much and search collapses; ignore it and search becomes
inefficient — Darwin learns the balance from data.
③ Architecture Mapper — weight-space breeding across heterogeneous
families. Attention × SSM crossover actually works.
Why It Matters
> Diagnose latent capabilities already encoded in open checkpoints,
> and recombine them — no gradients required.
Replies and critiques welcome 🙌
- 3 replies
reacted to unmodeled-tyler's post with 🚀 2 months ago
Post
3017
Just started a fun project!
unmodeled-tyler/DoW-UFO-UAP-1
I'm getting the recently released DoW UFO/UAP documents (https://war.gov/ufo) cleaned and converted into a dataset here on Hugging Face!
There 161 different files in the gov release (pdfs, images, videos, audio, etc) and my current plan is to do it all in 1 dataset with 4 different shards - that way you can just call whichever tables you want/need when you import the dataset.
This is an ongoing project (I'm doing it on the side + my regular projects) so it's a bit of a growing entity. I'll also continuously refine the data over time to make sure it's as clean as possible.
Check it out! Who knows what you'll find in there?
unmodeled-tyler/DoW-UFO-UAP-1
I'm getting the recently released DoW UFO/UAP documents (https://war.gov/ufo) cleaned and converted into a dataset here on Hugging Face!
There 161 different files in the gov release (pdfs, images, videos, audio, etc) and my current plan is to do it all in 1 dataset with 4 different shards - that way you can just call whichever tables you want/need when you import the dataset.
This is an ongoing project (I'm doing it on the side + my regular projects) so it's a bit of a growing entity. I'll also continuously refine the data over time to make sure it's as clean as possible.
Check it out! Who knows what you'll find in there?
- 3 replies
liked 2
models 3 months ago
