Hugging Face's logo
Activity Feed

AI & ML interests

Abliteration, interpretability, training-free model modification, democratization of AI

Recent Activity
darkc0de  updated a model 11 days ago
heretic-org/XORTRON.CriminalComputing.LARGE.2026.3
0utsideness  updated a model 15 days ago
heretic-org/gemma-3-4b-it-heretic
0utsideness  published a model 15 days ago
heretic-org/gemma-3-4b-it-heretic
View all activity
DavidAU 
posted an update 7 days ago
view post
Post
3877
Gemma 3 27B - The record breaker (Heretic'ed (uncensored) ; then training on Unsloth):

arc_challenge,arc_easy,boolq,hellaswag,openbookqa,piqa, winogrande
0.661 ,0.816 ,0.878,0.763 ,0.464 ,0.808 ,0.762

For comparison:
Qwen3.5-27B-Text
qx86-hi 0.443,0.498,0.857,0.701,0.372,0.770,0.752

Trained on a HERETIC uncensored base too ;

DavidAU/Gemma3-27B-it-vl-Polaris-HI16-Heretic-Uncensored-INSTRUCT
darkc0de 
updated a model 11 days ago
darkc0de 
posted an update 13 days ago
view post
Post
8211
1440GB of VRAM is incredibly satisfying 😁
·
DavidAU 
posted an update 14 days ago
view post
Post
6166
The "ERNIE" 21B MOE Distill High Reasoning Fine Tune Invasion:

3 Ernie 21B-A3B MOE Models (64 experts) fine tuned with Unsloth using Gemini Pro 3, Claude 4.5 Opus, and GLM 4.7 Flash high reasoning datasets.

All benched, all exceeding org model specs too.

https://huggingface.co/DavidAU/models?search=ernie

Enjoy the freedom and added power.
  • 1 reply
·
0utsideness 
updated a model 15 days ago
0utsideness 
published a model 15 days ago
0utsideness 
in heretic-org/Phi-4-mini-reasoning-heretic 16 days ago

Set base model
#1 opened 16 days ago by
MuXodious
MuXodious 
in heretic-org/Phi-4-mini-reasoning-heretic 16 days ago

Set base model
#1 opened 16 days ago by
MuXodious
MuXodious 
updated a model 16 days ago
0utsideness 
updated a model 16 days ago
0utsideness 
published a model 16 days ago
DavidAU 
posted an update 18 days ago
view post
Post
6569
Gemma 3 (1b, 4b, 12b and 27b) - Uncensored full Reasoning/Thinking models fine tuned using top distill datasets.

20 Gemma 3 models 1B, 4B, 12B and 27B with full reasoning using GLM 4.7 Flash, GPT, Claude and Gemini datasets and more fully fine tuned using Unsloth.

Most models are Heretic'ed (uncensored) first, and tuned second.
This vastly improves the model.

Models are also bench marked and in almost all cases exceed org model metrics - and in some cases by a lot.

Enjoy the freedom and more powerful THINKING/REASONING and UNCENSORED Gemma 3s !

https://huggingface.co/collections/DavidAU/gemma-3-reasoning-thinking-models-incl-uncensored

UPDATE: Benchmarks added for almost all models, including "VS" with Heretic (untuned) source models too.
MuXodious 
published a model 19 days ago
MuXodious 
updated a model 20 days ago
MuXodious 
published a model 20 days ago
MuXodious 
updated a model 21 days ago
MuXodious 
published a model 21 days ago
p-e-w 
updated a Space 21 days ago
p-e-w 
published a Space 21 days ago
DavidAU 
posted an update 28 days ago
view post
Post
7280
Tiny but mighty: LFM 1.2B - 11 Distill / Fine tunes : Exceeding all benchmarks at 300-700+ T/S on GPU, 60+ T/S CPU.

Almost all exceed LFM 1.2B Benchmarks - which are already very impressive.
All benchmarks posted.

A specialized merge of multiple of these fine tunes by @nightmedia FAR exceeds the benchmarks set by the already impressive LFM.

(LFM2.5-1.2B-MEGABRAIN-Thinking-Polaris-ClaudeHOPUS-Deepseek-GLM)

Included are GLM 4.7 Flash, DeepSeek, Claude, Kimi V2 and other distill fine tunes.

Here is the collection ( Quants by MRadermarcher).

https://huggingface.co/collections/DavidAU/lfm-12b-sota-400-700-t-s-enhanced-fine-tunes-distills

UPDATE:
Now with 9 more versions , fully uncensored, heretic too.
And 5 additional non-heretic.
·