In a Training Loop 🔄

David Belton PRO

DavidAU

AI & ML interests

Application(s) of single/multiple LLMs in specialized use cases & automation tasks. LLM, Prompt , System Role and Parameter engineering VIA chat / API. 2700+ merge models, over 600 fine tunes, over 1000 models published. DISCORD: David_AU [drawless111]

Recent Activity

updated a model about 15 hours ago

DavidAU/MN-GRAND-23.5B-Gutenberg-UNCENSORED-V2-GLM4.7-Thinking

updated a model about 15 hours ago

DavidAU/MN-GRAND-23.5B-Gutenberg-UNCENSORED-V2-GLM4.7-Thinking-NEO-Imatrix-GGUF

new activity about 15 hours ago

DavidAU/Mistral-MOE-4X7B-Dark-MultiVerse-Uncensored-Enhanced32-24B-gguf:Which model should I choose?

View all activity

Organizations

updated 2 models about 15 hours ago

DavidAU/MN-GRAND-23.5B-Gutenberg-UNCENSORED-V2-GLM4.7-Thinking

Text Generation • 23B • Updated about 15 hours ago • 109 • 1

DavidAU/MN-GRAND-23.5B-Gutenberg-UNCENSORED-V2-GLM4.7-Thinking-NEO-Imatrix-GGUF

Text Generation • 23B • Updated about 15 hours ago • 4.84k • 1

New activity in DavidAU/Mistral-MOE-4X7B-Dark-MultiVerse-Uncensored-Enhanced32-24B-gguf about 15 hours ago

Which model should I choose?

#5 opened 2 days ago by

Stefan13015

New activity in DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF about 15 hours ago

Are any future variants planned?

#13 opened 1 day ago by

markgb1

New activity in Gryphe/Gemma-4-31B-StyleTune about 16 hours ago

Excellent !

👍 1

#6 opened about 16 hours ago by

DavidAU

liked a dataset about 16 hours ago

Gryphe/Opus-4.6-Reasoning-24k

Viewer • Updated 4 days ago • 24.1k • 609 • 17

liked a model about 17 hours ago

Gryphe/Gemma-4-31B-StyleTune

Text Generation • 33B • Updated about 3 hours ago • 97 • 27

New activity in DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF about 18 hours ago

Didn't match up to the 'warnings' and labels, unfortunately.

#14 opened 1 day ago by

J3G3

New activity in DavidAU/Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MAX-NEOCODE-Imatrix-GGUF 1 day ago

Re-upload request: Qwen3.5-9B-DeepSeek-3.2-Intense-Auto-Variable-Thinking (404 since ~June 11)

👍🔥 1

#2 opened 3 days ago by

AfterMeaning

New activity in mradermacher/model_requests 1 day ago

Looking for the original .safetensors for DavidAU/Qwen3.5-9B-DeepSeek-3.2-Intense-Auto-Variable-Thinking

#2545 opened 3 days ago by

AfterMeaning

posted an update 1 day ago

Post

813

Going Old School "FULL CREATIVE" with "New Thinking":

MN-GRAND-23.5B-Gutenberg-UNCENSORED-V2-GLM4.7-Thinking

The strongest, most creative (and uncensored) model made up of 3 top Mistral Nemo fine tunes, franken-merged together into an 81 layer model then trained via Unsloth with GLM 4.7 Flash thinking/reasoning dataset.

Features hybrid thinking/instruct structure as well plus updated with modern jinja template too. Tuning has stabilized the "franken-merge" into a class 1 model that operates perfectly.

The talents of some of the best tuners merged into one giant model.
Several examples and detailed instructions.

And this model is very smart too.

NEO Imatrix GGUFS:
DavidAU/MN-GRAND-23.5B-Gutenberg-UNCENSORED-V2-GLM4.7-Thinking-NEO-Imatrix-GGUF

Source / Full Precision:
DavidAU/MN-GRAND-23.5B-Gutenberg-UNCENSORED-V2-GLM4.7-Thinking