🎓 Working on research...

Mithula Artigala PRO

mithulaartigala

91 17 103

AI & ML interests

I love RL!

Recent Activity

upvoted a changelog 1 day ago

A New Main Search UI

new activity 2 days ago

ricursiveAI/Ripple-65B-Preview:Preview tag

posted an update 2 days ago

I released my first research paper. You can read it here: https://github.com/mithulaartigala/grahwim-paper/blob/main/GraHWIM.pdf Its about utilizing energy from a source to its max potential. its for an inter school EC activity.

View all activity

Organizations

None yet

Posts 8

Post

I released my first research paper. You can read it here: https://github.com/mithulaartigala/grahwim-paper/blob/main/GraHWIM.pdf

Its about utilizing energy from a source to its max potential.

its for an inter school EC activity.

Post

3,108

here is my qwen is BETTER than the human brain:

human-brain-bf16.gguf:
- no cuda support
- 3.8B old model BTW
- BAD information retention
- the gguf files doesn't even load
- no Q4KM (god did this intentionally to piss off the llama.cpp community trust)
- no finetunability :(
- NOT opensource
- training code is hidden, AND expects us to reverse engineer it (genuinely messed up, and disrespectful to the opensource community)

now, qwen on the other hand:
- available cuda support ✅
- very very new (and gets contant updates) ✅
- VERY good information retention ✅
- GGUF files loads properly ✅
- Q4_K_M support available ✅
- very fine tunable ✅
- open source as it can possibly get ✅
- many code and datasets are free and open source ✅

verdict: qwen beter ✅✅✅ 👍