Soraya Hoggarth

somersetent's activity

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

upvoted 14 collections 20 days 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. • 111 items • Updated 12 days ago • 27

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. • 62 items • Updated Jul 9 • 20

MOE - Reasoning - Gated IQ Multi-Tier Models

Collection

MOE models using a unique custom internal structure to augment reasoning/thinking up to 300 % which then switches during generation mode. • 8 items • Updated Jul 7 • 5

Dark Champion Collection MOE - Mixture Of Experts

Collection

Uncensored ; you can dial up/down the number of experts activated. 128 k context. • 8 items • Updated Jul 7 • 9

Rogue Creative Series - GGUF / Incl Source too.

Collection

Based on Llama 3.2 this is a specialized creative series. L3.2 has strong instruction following. Repos including example generations. Source below too • 8 items • Updated Jul 7 • 2

Dark Planet Series (see "source" coll. for FP)

Collection

A dark bias collection of models for any creative use such as writing, fiction, storytelling, role play and other uses. Example gens at each repo. • 31 items • Updated Jul 7 • 50

WS - Wordstorm 10 Part Series incl Full Source

Collection

Series about Dare-Ties and Random pruning. Parts 1-5 have detailed generations. Full Source pages include links to more quants, incl Imatrix ggufs. • 6 items • Updated Jul 7 • 1

WS - Dark Planet Wordstorm Project - Random Prune / Form.

Collection

Models using the org Dark Planet 8B formula, with random pruning / density, to create new Dark Planet versions with new abilities / generation. • 5 items • Updated Jul 7 • 5

Coders and Programmers: 4B Models with Brainstorm 20x (6B)

Collection

4B Qwen 3 models for general and/or coding usage, with Brainstorm 20x added. • 3 items • Updated Jul 7 • 3

Coders and Programmers: 0.8B, 2.4B, 3.4B

Collection

Micro, Fused and Brainstorm Coders using Qwen 3. • 4 items • Updated Jul 7 • 2

Coders and Programmers: 128 expert / A3B Coders

Collection

Coder models based on Qwen3 for coding and programming. Part of the coder collection. • 8 items • Updated Jul 9 • 4

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

Collection

Models (0.8B to 87B) in regular, "reasoning", "Brainstorm", MOE (1x to 8x / 128 experts), and expanded to create better and stronger code, faster. • 68 items • Updated 12 days ago • 59

Grand Horror 16.5B+ Horror and Fiction Generation

Collection

NSFW, Horror, Fiction Generation models of different sizes and calibrations. Can be used for all genres of fiction. [ NEWEST -> bottom of the list ] • 156 items • Updated 26 days ago • 84

Dark MOEs - Mixture of Experts - Uncensored Creative Models

Collection

Listed in terms of most power ; including both GGUF and Source. Link to quants on source pages too. You can dial up or down the number of experts. • 23 items • Updated 23 days ago • 25

upvoted 2 collections 21 days ago

Heretic - Abliterated, Uncensored, Unrestricted POWER.

Collection

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 16 days ago • 147

Qwen 3.6 - Reg/Uncensored 9b, 12b, 21b, 27b, 40B

Collection

Fine tuned Qwen 3.6/3.8 models, including source and GGUF from 9B and up. 9B,12B, 21B and 40B are custom built by me. Tuning : Unsloth / COLD FUSION. • 19 items • Updated 6 days ago • 47

upvoted 4 collections 25 days ago

Dark / Evil / NSFW Reasoning Models (gguf/source)

Collection

Models that are dark/evil/corrupt (and many times NSFW!) to begin with then I add reasoning/thinking to them to make them even... ahh... better. • 136 items • Updated 16 days ago • 290

Unsloth Dynamic 2.0 Quants

Collection

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 121 items • Updated about 7 hours ago • 813

Qwen3.6

Collection

4 items • Updated Apr 22 • 492

DeepSeek-V4

Collection

8 items • Updated 15 days ago • 860