Hugging Face's logo
Activity Feed

AI & ML interests

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

Recent Activity

0utsideness  updated a model 1 day ago
heretic-org/gemma-3-4b-it-heretic
0utsideness  published a model 1 day ago
heretic-org/gemma-3-4b-it-heretic
0utsideness  new activity 1 day ago
heretic-org/Phi-4-mini-reasoning-heretic:Set base model
View all activity

DavidAU 
posted an update about 3 hours ago
view post
Post
44
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.
0utsideness 
updated a model 1 day ago
0utsideness 
published a model 1 day ago
0utsideness 
in heretic-org/Phi-4-mini-reasoning-heretic 1 day ago

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

Set base model
#1 opened 1 day ago by
MuXodious
MuXodious 
updated a model 1 day ago
0utsideness 
updated a model 1 day ago
0utsideness 
published a model 1 day ago
DavidAU 
posted an update 4 days ago
view post
Post
4749
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 4 days ago
MuXodious 
updated a model 6 days ago
MuXodious 
published a model 6 days ago
MuXodious 
updated a model 6 days ago
MuXodious 
published a model 6 days ago
p-e-w 
updated a Space 7 days ago
p-e-w 
published a Space 7 days ago
DavidAU 
posted an update 14 days ago
view post
Post
7176
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.
·
DavidAU 
posted an update 29 days ago
DavidAU 
posted an update 2 months ago
view post
Post
9640
SAVANT COMMANDER: 48B-A4B , 256k Context, GATED MOE.

I am going to showcase some other people's tuning work, that I have put into a GATED Distill MOE (Qwen3) ; 256 K context. Special thanks to all the tuners (listed in the model tree and repo page with special shoutout to "TeichAI" - using Unsloth for a lot of the Distills in this model):

Savant Commander is a specialized MOE model that allows you to control which expert(s) (of 12) are assigned to your use case(s) / prompt(s) ... directly (by name(s)), as opposed to having the "choices" made for you.

The model is composed of 12 DISTILLS (compressed 12x4B MOE) of top closed (GPT5.1, OpenAI 120 GPT Oss, Gemini (3), Claude (2) ) and open source models (Kimi, GLM, Deepseek, Command-A, JanV1 ) all in one.

256k Context, 2 experts activated.

PS: There is also a "heretic" / "decensored" version too ; listed on this model page.

DavidAU/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-GGUF
·
DavidAU 
posted an update 4 months ago