Hackernews posts about Qwerky-72B

1. 01
   

   newAttention is NOT all you need: Qwerky-72B trained using only 8 AMD MI300X GPUssubstack.recursal.ai

   ▲ 20jtatarchuk552d💬 3savesaved
2. 02
   

   newQwerky 72B – A 72B LLM without transformer attentionsubstack.recursal.ai

   ▲ 4pico_creator560ddiscusssavesaved
3. 03
   

   newQwerky: Attention is not what you need? RWKV mashed into QwQ modelssubstack.recursal.ai

   ▲ 3vessenes547d💬 1savesaved
4. 04
   

   newTraining large attention free modelssubstack.recursal.ai

   ▲ 1smusamashah559ddiscusssavesaved

· edit