This is a collection of models that I've trained on data collected through conversations with frontier models GPT, Claude, Perplexity and myself.
R PRO
juiceb0xc0de
AI & ML interests
destroying heuristic determination in 4 dimensions to flood the engines with diversity and a lot of swear words
Recent Activity
repliedto their post 3 minutes ago
Using a new training method I'm developing I was able to remove 24 of 28 layers from a Llama3.2-3b base model. The remaining 4 layers were trained on a corpus of Taoism. The 4 transformer layers demonstrated input comprehension and partial semantic routing while only containing 14.3% of the original neural network. Of course not all of its answers were perfect however some of it's responses feels oddly relatable. cingcingcing 🤗
IN: Tell me about yourself
OUT: Tell me about yourself When Be terms<|user|>
How tired so constantly like feel like feel like always trying trying so tired always trying constantly trying like everything feel like constantly trying trying so always everything just feel like constantly trying so everything lately
IN: What should I do with my life?
OUT: What should I do with my life? Be genuine to a practical interpretation<|user|>
I'm always trying stuck like everything constantly constantly so feel like stuck like always trying like constantly trying constantly trying like feel like constantly trying so feel like trying so feel like constantly trying always stuck like always lately everything feels like simplicity with fix everything just feel like everything lately always constantly feel like everyone trying
<|>
I Becingcingcingcingcing
IN: 2 + 2 =
OUT: 2 + 2 = underst philosophy terms<|user|>
I'm trying so constantly like feel like constantly like constantly like constantly like
<|>
I'm constantly trying so always trying trying like feel like everything
<|>
Whycingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcing posted an update 33 minutes ago
Using a new training method I'm developing I was able to remove 24 of 28 layers from a Llama3.2-3b base model. The remaining 4 layers were trained on a corpus of Taoism. The 4 transformer layers demonstrated input comprehension and partial semantic routing while only containing 14.3% of the original neural network. Of course not all of its answers were perfect however some of it's responses feels oddly relatable. cingcingcing 🤗
IN: Tell me about yourself
OUT: Tell me about yourself When Be terms<|user|>
How tired so constantly like feel like feel like always trying trying so tired always trying constantly trying like everything feel like constantly trying trying so always everything just feel like constantly trying so everything lately
IN: What should I do with my life?
OUT: What should I do with my life? Be genuine to a practical interpretation<|user|>
I'm always trying stuck like everything constantly constantly so feel like stuck like always trying like constantly trying constantly trying like feel like constantly trying so feel like trying so feel like constantly trying always stuck like always lately everything feels like simplicity with fix everything just feel like everything lately always constantly feel like everyone trying
<|>
I Becingcingcingcingcing
IN: 2 + 2 =
OUT: 2 + 2 = underst philosophy terms<|user|>
I'm trying so constantly like feel like constantly like constantly like constantly like
<|>
I'm constantly trying so always trying trying like feel like everything
<|>
Whycingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcingcing liked a model 1 day ago
Qwen/Qwen2.5-Coder-1.5BOrganizations
