ponzi

ponzles's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 13 days ago

On Path to Multimodal Generalist: General-Level and General-Bench

Paper • 2505.04620 • Published May 7 • 82

upvoted a collection 17 days ago

ERNIE 4.5

Collection

collection of ERNIE 4.5 models. "-Paddle" models use PaddlePaddle weights, while "-PT" models use Transformer-style PyTorch weights. • 25 items • Updated 8 days ago • 151

upvoted a collection 18 days ago

BGE

Collection

30 items • Updated May 20 • 125

upvoted a collection about 2 months ago

DeepSeek-R1

Collection

10 items • Updated May 29 • 756

upvoted 7 collections 3 months ago

Qwen2.5-Omni

Collection

End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 • 7 items • Updated May 21 • 149

Josiefied and Abliterated Qwen3

Collection

Abliterated, and further fine-tuned to be the most uncensored models available. • 15 items • Updated 29 days ago • 22

Qwen3-abliterated

Collection

19 items • Updated 17 days ago • 22

Qwen3

Collection

72 items • Updated Jun 15 • 861

GLM-4-abliterated

Collection

3 items • Updated Apr 19 • 3

GGUF Image Model Quants

Collection

List of GGUF quants for text to image base models. • 31 items • Updated May 8 • 58

Llama 4

Collection

Llama 4 release • 13 items • Updated Apr 29 • 576

upvoted a collection 4 months ago

Thinking / Reasoning Models - Reg and MOEs.

Collection

QwQ,DeepSeek, EXONE, DeepHermes, and others "thinking/reasoning" AIs / LLMs in regular model type, MOE (mix of experts), and Hybrid model formats. • 108 items • Updated 2 days ago • 9

upvoted a collection 5 months ago

🧠 Reasoning datasets

Collection

Datasets with reasoning traces for math and code released by the community • 24 items • Updated May 19 • 161

upvoted an article 5 months ago

view article

Article

Open-source DeepResearch – Freeing our search agents

By and 4 others •

Feb 4

• 1.27k

upvoted 4 collections 6 months ago

Roleplay

Collection

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

Qwen2.5 Series

Collection

10 items • Updated Oct 25, 2024 • 3

DeepSeek-R1-abliterated

Collection

9 items • Updated May 30 • 110

Eagle 2

Collection

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. • 10 items • Updated 8 days ago • 36

upvoted 2 collections 7 months ago

Ink

Collection

Cursed roleplaying. • 4 items • Updated May 30 • 4

MOE/Mixture of Experts Models (see also "source" cll)

Collection

Mixture of Expert Models by me. This leverages the power of multiple models at the same time during generation for next level performance. • 88 items • Updated 3 days ago • 9