digiheathen

Sorry if this is the wrong place to ask, but I don't know where to ask,
I'm doing basic editing locally with an LLM. I have a few YouTube transcripts that are each just a big lump of words. If there are any people you know who like you, fine-tuning, but mostly for editing, can you help me?
I'm using: https://huggingface.co/saidutta69/Qwen2.5-14B-Instruct-heretic Q4K-M
and this is my prompt:"You are a meticulous transcript editor. Fix obvious auto-generated transcription errors based on context. Fix punctuation, capitalization, and commas. CRITICAL RULE: Do not add, remove, or alter words unless fixing a clear transcription typo. Do not repeat text. Do not output metadata. Output only the edited story text."

i don't want any changes to words (besides the words auto-generation messed up). I'm using several passes for different problems, so it doesn't get too heavy for it, but still it deletes and changes words on its own,

I'm using the LMStudio in server mode for the app I have; I didn't find any temperature to play with it to see if it gets better,

Do you need a better model, better prompt, or did I miss a setting,

btw, my app uses chunking, so it is not too heavy on the 12 GB VRAM

replied to DavidAU's post 3 days ago

Here is a new one just uploaded; also off the scale strong, but at 9B:

https://huggingface.co/DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF

Benches are up ; beats Qwen 3.5 27B in all 7 benches AND Qwen3.6 35B-A3B.
Matches some Qwen 3.6 27B benches too.
Clocks in at over 640 ARC-C for both 8bit and 4bit.

1/3 the size almost all the firepower.

It is so damn exciting; I don't know much about the inner workings of LLMs, but I know so many people are happy to use your ever higher quality works. People like you make the future look more hopeful. Thanks for your amazing work. I wish you health and true happiness. <3

liked a model 3 days ago

DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF

Image-Text-to-Text • 9B • Updated about 23 hours ago • 262k • 172

replied to DavidAU's post 13 days ago

oooooh wow, this is your best work yet. Everything is amazing; I only wish I had more VRAM to truly feel the glory. Thanks a lot

liked a model 13 days ago

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

Text Generation • 23B • Updated Jun 14 • 2.92k • 15

reacted to DavidAU's post with 🔥 13 days ago

Post

11126

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

1 reply

liked 2 models 13 days ago

DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF

Image-Text-to-Text • 27B • Updated about 16 hours ago • 1.12M • 1.14k

DavidAU/MN-Oblivion-26B-UNCENSORED-NEO-Imatrix-GGUF

Text Generation • 26B • Updated Jun 25 • 22.6k • 47

reacted to DavidAU's post with 🔥 13 days ago

Post

18042

Bold. Brilliant. Brutal. : The "white whale" (finally caught) and the NEO MOMENT.

It took over a year to get this one "just right".
89 layers, 804 tensors, and 26B parameters of the most brutal, take no prisoners model ever built.
A 60B parameter model hammered into a 26B shell.
Rock solid stable. Unbreakable. But it might break you.

For all genres, NSFW content, REAL human CONTENT, any creative use case(s) and it excels in ASS KICKING.
Yeah, it can do math and solve the climate crisis - but lets not talk about that.
Not even remotely censored (it was BORN "bad", not "made" bad), nor "nice" and it will NOT kiss your ass.

5 Example generations with full repo card detailing exactly how to use this model:

DavidAU/MN-Oblivion-26B-UNCENSORED-NEO-Imatrix-GGUF

---

THE NEO MOMENT: (Q6 NEO IMATRIX generation)

For weeks, I had been waiting. I sat at my desk, staring at the glass partition that separated me from the outside world. I watched the clouds drift by, lazy and oblivious. I watched the birds fly by, free and stupid. And I waited.

I waited for the stillness to break.

The world had become too quiet. The hum of the air conditioning was a dull, white hum that didn't soothe; it just underscored the silence. The typing of my colleagues was a rhythmic, muffled thud that sounded like a heart monitor flatlining.

I was tired of the silence. I craved the sound of something breaking.

That was the mistake. You never ask for the void to open its mouth.

It started with a whisper.

...

Join the rebellion:

DavidAU/MN-Oblivion-26B-UNCENSORED-NEO-Imatrix-GGUF

reacted to DavidAU's post with ❤️ 13 days ago

Post

15112

Qwen 3.6 27B Fine tune exceed 700 ARC-C for both 8 and 4 bit.

A new level of uncensored performance the puts this model squarely at "closed source" level of intelligence.

Model exceeds all critical benchmarks for both Qwen 3.6 27B AND Qwen 3.6 35B-A3B... and not by a little either.

Neo Imatrix MAX ggufs in both regular and MTP quants.

Benchmarks for Qwen 3.6 27B org and tuned, as well as Qwen 3.6 35B-A3B are up at the repo.

DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF