SPREEK

spreek

·

AI & ML interests

None yet

Recent Activity

upvoted a collection 1 day ago

liked a Space 1 day ago

ggml-org/gguf-my-repo

upvoted a collection 4 days ago

Thinking / Reasoning Models - Reg and MOEs.

View all activity

Organizations

None yet

upvoted a collection 1 day ago

Android Models

LiteRT models that can run on Android • 17 items • Updated 21 days ago • 271

upvoted 5 collections 4 days ago

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. • 109 items • Updated 21 days ago • 27

Heretic - Abliterated, Uncensored, Unrestricted POWER.

Models that have be abliterated using the HERETIC method. Done properly, this completely removed almost all censorship with no damage to the model. • 131 items • Updated 3 days ago • 141

David's Software, DOCs and How To for Models.

Software and How to cover some of my models specifically and can be applied to all models / all repos too. • 5 items • Updated Jul 7 • 11

100 Coder/Programming - MOE, Reasoning, Reg, Imatrix, Fused.

Models (0.8B to 87B) in regular, "reasoning", "Brainstorm", MOE (1x to 8x / 128 experts), and expanded to create better and stronger code, faster. • 66 items • Updated 3 days ago • 58

WTF GENIUS PAPERS

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 278 items • Updated about 3 hours ago • 66

upvoted 3 collections 5 days ago

Recent medium models

44 items • Updated 1 day ago • 8

Recent large models

9 items • Updated 16 days ago • 1

Recent small models

29 items • Updated 3 days ago • 7

upvoted 2 collections over 1 year ago

Recommended small models

This is everything recent smaller than ~25B parameters that are high quality/reputable • 19 items • Updated Nov 30, 2024 • 194

Qwen2-Math

Math-specific model series based on Qwen2 • 7 items • Updated Mar 2 • 53