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. 500+ LLMs graded.

Recent Activity

updated a collection about 13 hours ago

Qwen 3 / 2.5 Reasoning/Thinking REG + MOEs.

updated a collection about 13 hours ago

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

updated a collection about 13 hours ago

100 Coder/Programming - MOE, Reasoning, Reg, Imatrix, Fused.

View all activity

Organizations

Posts 7

Post

2643

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

Post

5035

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.

View all Posts