Models I didn't make, but I quite like.
Bot PRO
inflatebot
AI & ML interests
"Potentially one of my biggest flaws is that I genuinely think that the science appreciates when you commit to a bit." - Tom ExtractionsAndIre
Recent Activity
reacted to mithulaartigala's post with 🧠 about 13 hours ago
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 ✅✅✅ 👍 reacted to mithulaartigala's post with 😔 about 13 hours ago
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 ✅✅✅ 👍 reacted to mithulaartigala's post with 🤝 about 13 hours ago
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 ✅✅✅ 👍Organizations
A reapplication of the Helium-3 process to Nemo analogues. Magnum V2 and Rosier.
The development versions of Helide which I consider to be better than the others.
Models I didn't make, but I quite like.
My favorite things that I've done, and the models I'd recommend anybody to use.
A reapplication of the Helium-3 process to Nemo analogues. Magnum V2 and Rosier.
The culmination of my first LLM project. Hybrid storytelling and RP model, with a focus on niche fetish content. (This will be a recurring theme.)
The development versions of Helide which I consider to be better than the others.