Jae Hutchinson

sirmyrrh

·

AI & ML interests

None yet

Recent Activity

reacted to AesSedai's post with 👍 17 days ago

Hi all, I'm posting this as sort of an informal notice + poll. I'm down to about 700GB free of HF space and there's MiniMax-M3 on the horizon, plus a couple other models I'd like to quant like the Nex-N2 Pro finetune. I've already super-squished all of my quant repositories to free up any LFS space that might have been lingering there, but I'm back near the cap again now. To free up some space, I'm planning to remove these three older GLM quants: - GLM-4.5: 1.23TB - GLM-4.6: 728GB - GLM-4.7: 787GB I'm open to other suggestions as well, and I'll wait a few days before removing anything in case someone wants to download a version before I get rid of them. Thanks! Edit 06/14/2026: I've created an organization https://huggingface.co/QuantPasture and moved the older GLM quants there. My GLM-4.6-Derestricted has migrated to ReadyArt: https://huggingface.co/ReadyArt/GLM-4.6-Derestricted-GGUF

reacted to grimjim's post with ➕ 17 days ago

I think it's clear in retrospect that "frankenmerges", which repeated blocks of layers, amounted to a crude approximation of looped transformers architecture, hence them able to work at all instead of just breaking. They lucked out due to much of the signal passing through residual streams being preserved and only modulated along the way. That said, not all models are suited for this. Models which feature ever-increasing magnitudes as inference progressess through layers risk exploding precision limits.

liked a model 4 months ago

Blazed-Forge/Gemma-4-Sphinsikus-Chronist-31B

View all activity

Organizations

upvoted 2 collections 5 months ago

Derestricted

Models abliterated using Norm-Preserving Biprojected Abliteration • 8 items • Updated Mar 18 • 25

T-34

Seize the means of token production. • 3 items • Updated Feb 9 • 3

upvoted a collection 6 months ago

Draconia-Overdrive-32B

11 items • Updated May 27, 2025 • 2

upvoted a collection 12 months ago

Roleplaying

Creativity at cost of context & knowledge • 5 items • Updated Dec 13, 2025 • 15

upvoted 5 collections over 1 year ago

XORTRON - Criminal Computing

Current Release Quality XORTRON Apps and Models • 3 items • Updated 2 days ago • 38

Falcon-H1

Falcon-H1 Family of Hybrid-Head Language Models (Transformer-SSM), including 0.5B, 1.5B, 1.5B-Deep, 3B, 7B, and 34B (pretrained & instruction-tuned). • 33 items • Updated Aug 13 • 60

BlackSheep

Generates unrestricted and potentially hazardous information, exploring the full extent of AI capabilities. • 65 items • Updated May 19 • 12

YOLOs

My YOLos • 2 items • Updated Feb 9, 2025 • 4

GLM-4

GLM-4 Open Models • 14 items • Updated Jun 30, 2025 • 126

upvoted 4 collections almost 2 years ago

OpenCrystal

OpenCrystal Models • 5 items • Updated Nov 20, 2024 • 4

Current Recommendation

My current Recommendations. • 5 items • Updated 16 days ago • 4

Merges

Stuff I've cooked myself, for better or for worse. • 10 items • Updated Aug 30 • 3

7-9B Models

light model merges • 6 items • Updated Mar 2 • 2

upvoted an article almost 2 years ago

Article

The Great LLM Showdown: Amy's Quest for the Perfect LLM

wolfram

•

Jul 9, 2024

• 14

upvoted 5 collections almost 2 years ago

200+ Roleplay, Creative Writing, Uncensored, NSFW models.

Oldest models listed first, with Newest models at bottom of the page. Most repos have full examples, instructions, best settings and so on. • 287 items • Updated 2 days ago • 1.15k

Mytho Series (Llama 2)

Legacy models. • 5 items • Updated Jun 16 • 10

Rombos-LLM-V2.6

My latest and greatest models • 4 items • Updated Oct 17, 2024 • 10

magnum-v2.5

3 items • Updated Aug 21, 2024 • 14

Final RP Mistral-v0.1 (21-32k context) Models

12 items • Updated Jun 6, 2025 • 9

upvoted a collection about 2 years ago

Nice to have

My highly recomended models • 16 items • Updated Mar 2 • 1