PRECOMPUTED AI WEIGHTS
! INNOVATIONS ARE USED INSTEAD REFUSALS !
Known Training Algos:
- Backpropagation
- Forward Forward
- Predictive Coding
- Q-Learning ?
-....
|for correct ds1307 pinout 8-stars(0-14B models Q4)| for Diffusion LLM 9-stars | Teach llms on ASCII/Text Based STL Modeling , ic pinouts .optionaly:patents. |context editing| .exact size of all obj dimentions. Virtualization of ai/ml in mcu .Funding require.///until llms are weak///
https://github.com/sponsors/jelspace
https://ko-fi.com/21world
https://rumble.com/c/c-5865836
https://www.buymeacoffee.com/21world
Qwen 3 Fine tuning >> MoE. Update the experiment thread to include config and script for fine-tuning the Qwen3-30B-A3B model.
The goal is to make a low latency non-thinking model for a daily driver coding, so 3 billion parameters active should be perfect.
✔️ training running ✔️ evals running ⏭️ improve dataset
The moe isn't going to fit into colab's A100 even with quantization (🙏 @UnslothAI ). So I've been working on HF spaces' H100s for this. Everything is available in the tread and I'll share more tomorrow.