ponzi's picture

ponzi

ponzles

·

AI & ML interests

None yet

Recent Activity

upvoted a collection 4 days ago

D_AU - Thinking / Reasoning Models - Reg and MOEs.

reacted to OFT's post with 😔 4 days ago

Today I decided to cancel my PRO subscription for Hugging Face. I had a lot of fun with it but with the current changes to API and allowed limits I think it isn't worth it anymore. So I just turned everything off and cancelled my subscription. It feels like one of these movies scenes where you see an old computerlab and someone putting big white sheets over it and closing the door behind him. I am not going, I am not gone, but watching through the glass window of the door that I just closed.

liked a model 4 days ago

TareksLab/L-MERGE2a

View all activity

Organizations

None yet

ponzles's activity

upvoted a collection 4 days ago

D_AU - Thinking / Reasoning Models - Reg and MOEs.

QwQ,DeepSeek, EXONE, DeepHermes, and others "thinking/reasoning" AIs / LLMs in regular model type, MOE (mix of experts), and Hybrid model formats. • 38 items • Updated 6 days ago • 4

upvoted a collection about 1 month ago

🧠 Reasoning datasets

Datasets with reasoning traces for math and code released by the community • 18 items • Updated 1 day ago • 115

upvoted an article about 2 months ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.19k

upvoted 3 collections about 2 months ago

Roleplay

roleplaying/creative writing models i've made • 5 items • Updated Aug 4, 2024 • 1

Qwen2.5 Series

10 items • Updated Oct 25, 2024 • 4

DeepSeek-R1-abliterated

7 items • Updated Jan 31 • 93

upvoted a collection 2 months ago

Eagle 2

Eagle 2 is a family of frontier vision-language models with vision-centric design. The model supports 4K HD input, long-context video, and grounding. • 9 items • Updated 1 day ago • 31

upvoted 10 collections 3 months ago

Ink

Cursed roleplaying. • 4 items • Updated Feb 16 • 4

D_AU- MOE/Mixture of Experts Models (see also "source" coll)

Mixture of Expert Models by me. This leverages the power of multiple models at the same time during generation for next level performance. • 25 items • Updated 6 days ago • 6

EXAONE-3.5

EXAONE 3.5 language model series including instruction-tuned models of 2.4B, 7.8B, and 32B • 10 items • Updated 10 days ago • 107

Meta's Llama 3.3 models & evals

2 items • Updated Dec 13, 2024 • 58

The Big Benchmarks Collection

Gathering benchmark spaces on the hub (beyond the Open LLM Leaderboard) • 13 items • Updated Nov 18, 2024 • 214

Sana

⚡️Sana: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer • 21 items • Updated 12 days ago • 89

Open LLM Leaderboard best models ❤️‍🔥

A daily uploaded list of models with best evaluations on the LLM leaderboard: • 65 items • Updated 7 days ago • 568

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

Newest models at bottom of the page. Please review the org model card for special instruction(s). New Models / Models by D_AU appear at the bottom. • 251 items • Updated 4 days ago • 162

DeepSeek-VL2

5 items • Updated Feb 9 • 72

LLaMA-O1-1129 Datasets, Models, Codes and Papers

8 items • Updated Dec 3, 2024 • 18

upvoted a collection 4 months ago

llama3.3-abliterate

1 item • Updated Dec 12, 2024 • 4