Qwen/Qwen3.8-27B
Image-Text-to-Text • 28B • Updated • 1.37M • • 11.6k
🔄 In a Training Loop
The Supreme GGUF-SafeTensors Guy
GGUFGuy
AI & ML interests
I like llms
Recent Activity
new activity 33 minutes ago
CaptiveDreamer/CaraArchive:🚩 Report: Other repliedto Banaxi-Tech's post about 5 hours ago
We're releasing BananaMind 2.1 Unified, a 35M three-tower relay model where the two output towers can only talk to each other through a silent middle tower that has no output head and no loss term.
Tower B trains entirely on indirect gradient. It was never told what to predict. It woke up anyway. Jacobian lens shows it carrying the correct answer ("Paris", "oxygen", "blue") at its deepest layer. Its bridge gates grew 4-47x from init. Feed it from only one side and the representations collapse to junk — it needs both outer towers to become semantic.
The PIQA result is the cleanest demonstration: Tower A alone scores 50.11 (chance). Tower C alone 52.12. Full system 61.75. All physical reasoning lives in the integration. The 35M three-tower beats the 50M single-tower BananaMind 2 Medium on PIQA.
Trained on 38B tokens in ~7.5 hours on 8x RTX PRO 6000. Ships with 7 ablation modes so you can surgically cut the model apart without retraining. Full training logs, J-lens fits, and eval outputs for every mode included.
This is a research model. It is interesting because you can take it apart.
https://huggingface.co/BananaMind/BananaMind-2.1-Unified
Follow us for more:
https://huggingface.co/BananaMind
@Banaxi-Tech updated a model about 6 hours ago
GGUFGuy/hgbnOrganizations
liked a
model 6 days ago
liked a
model 7 days ago
liked 2
models 8 days ago
liked a
Space 15 days ago
liked a
dataset about 1 month ago
