D_AU - Reasoning Adapters / LORAs -> Any model to reasoning

DavidAU 's Collections

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

D_AU - Grand Horror 16.5B+ Horror and Fiction Generation

D_AU - Qwen 3 - Horror / Neo Imatrix / Max Qs / 32-256k ctx

D_AU - MOE - Reasoning - Gated IQ Multi-Tier Models

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

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

D_AU - Qwen 3 / 2.5 Reasoning/Thinking REG + MOEs.

D_AU - Thinking / Reasoning Models - Reg and MOEs.

D_AU - Qwen3 4B - Fiction on Fire - Merge/pruning series.

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

D_AU - Gemma3 - Modified / Augumented Models

D_AU - Gemma The Writer Series - GGUF / Source)

D_AU - Brainstorm - Augmented and Expanded Reasoning

D_AU - Rogue Creative Series - GGUF / Incl Source too.

D_AU - Reasoning Adapters / LORAs -> Any model to reasoning

D_AU - Reasoning Source files for GGUF, EXL2, AWQ, GPTQ

D_AU - Source files for GGUF, EXL2, AWQ, GPTQ, HQQ etc etc

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

D_AU - Higher Precision GGUFs / Imatrix Plus

200+ Roleplay, Creative Writing, Uncensored, NSFW models.

D_AU - Wordstorm 10 Part Series incl Full Source

D_AU - X-Quants - State of Mind Adjusted Quants

D_AU - Experiments in Merging Top Models

Mini-MOEs - Mixture of Experts 2x, x4 and x8

Long Context - 16k,32k,64k,128k,200k,256k,512k,1000k

Instruct Models - Better instruction following.

Solar Models (Q6) - Exceptional Performance

1b,3b,4b - Upgraded Quants Q6/Q8

10B / 10.7B / 11B models (except MOEs)

High Quality / Hard to Find

50 Leaderboards, Benchs, GGUF Tools, and Utilities

2000+ Run LLMs here - Directly in your browser

31 - Run Image / Video LLMs in your browser

D_AU - Reasoning Adapters / LORAs -> Any model to reasoning

updated 22 days ago

Lora adapters and methods to turn any model into a reasoning model for multiple types of models including Llama, Mistral, Qwen and more.

Upvote

DavidAU/LORA-DeepSeek-R1-Distill-Llama-8B-rank-64-INSTRUCT-adapter

Text Generation • Updated Feb 26 • 11 • 1
DavidAU/Mistral-Small-3-Reasoner-s1-24B-LORA-256-RANK

Text Generation • Updated Mar 10 • 15 • 3
DavidAU/LORA-DeepSeek-R1-Distill-Llama-8B-rank-64-BASE-adapter

Text Generation • Updated Feb 26 • 9
DavidAU/LORA-DeepSeek-R1-Distill-Llama-8B-rank-128-INSTRUCT-adapter

Text Generation • Updated Feb 26 • 30
DavidAU/LORA-DeepSeek-R1-Distill-Llama-8B-rank-128-BASE-adapter

Text Generation • Updated Feb 26 • 25 • 1
DavidAU/LORA-DeepHermes-R1-Reasoning-Llama-8B-rank-64-adapter

Text Generation • Updated Feb 26 • 12
DavidAU/LORA-DeepHermes-R1-Reasoning-Llama-8B-rank-128-adapter

Text Generation • Updated Feb 26 • 55 • 1
DavidAU/LORA-DeepHermes-R1-Reasoning-Llama-8B-rank-256-adapter

Text Generation • Updated Feb 26 • 36 • 1
DavidAU/LORA-DeepHermes-R1-Reasoning-Llama-8B-rank-512-adapter

Text Generation • Updated Feb 26 • 8 • 1
DavidAU/LORA-DeepHermes-R1-Reasoning-Llama-8B-rank-32-adapter

Text Generation • Updated Feb 26 • 12
DavidAU/How-To-Use-Reasoning-Thinking-Models-and-Create-Them

Text Generation • Updated Apr 4 • 8
DavidAU/DeepSeek-R1-Distill-Qwen-14B-LORA-64-RANK

Text Generation • Updated Mar 10 • 9
DavidAU/DeepSeek-R1-Distill-Qwen-14B-LORA-128-RANK

Text Generation • Updated Mar 10 • 10
DavidAU/DeepSeek-R1-Distill-Qwen-14B-LORA-256-RANK

Text Generation • Updated Mar 10 • 58
DavidAU/Mistral-Nemo-12B-LORA-64-RANK

Text Generation • Updated Mar 10 • 10
DavidAU/Mistral-Nemo-12B-LORA-32-Rank

Text Generation • Updated Mar 10 • 28
DavidAU/Mistral-Nemo-12B-LORA-128-RANK

Text Generation • Updated Mar 10 • 29
DavidAU/Mistral-Nemo-12B-LORA-256-RANK

Text Generation • Updated Mar 10 • 15
DavidAU/Mistral-Small-3-Reasoner-s1-24B-LORA-64-RANK

Text Generation • Updated Mar 10 • 12
DavidAU/Mistral-Small-3-Reasoner-s1-24B-LORA-128-RANK

Text Generation • Updated Mar 10 • 8
DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters

Updated 29 days ago • 121

Note Document detailing all parameters, settings, samplers and advanced samplers to use not only my models to their maximum potential - but all models (and quants) online (regardless of the repo) to their maximum potential. Included quick start and detailed notes, include AI / LLM apps and other critical information and references too. A must read if you are using any AI/LLM right now.
DavidAU/AI_Autocorrect__Auto-Creative-Enhancement__Auto-Low-Quant-Optimization__gguf-exl2-hqq-SOFTWARE

Text Generation • Updated 29 days ago • 52

Note SOFTWARE patch (by me) for Silly Tavern (front end to connect to multiple AI apps / connect to AIs- like Koboldcpp, Lmstudio, Text Gen Web UI and other APIs) to control and improve output generation of ANY AI model. Also designed to control/wrangle some of my more "creative" models and make them perform perfectly with little to no parameter/samplers adjustments too.

Upvote