Cosmos-T2-80M-Test
87.60M params 12 layers RoPE + RMSNorm + SwiGLU + GQA Engram on CPU
Trained on wop/XXXXXL-chain-of-thought · Model repo
⚠️ Research/demo model — small, may hallucinate freely. Keep temperature low for stable outputs.
Send a message to start…
0 2
1 200
64 1028
16 1028