minus-squaremadmax_br5@alien.topBtoLocalLLaMA@poweruser.forum•Is there a technical reason that distributed LLMs don't exist?linkfedilinkEnglisharrow-up1·1 year agoI don’t know if there’s much value there when LORA’s are easily portable — you can just select the right lora as needed. One base model instance on one machine, many potential experts. This has been demonstrated. linkfedilink
madmax_br5@alien.topB to LocalLLaMA@poweruser.forumEnglish · 1 year agoAnyone get Amazon’s long-context MistralLite to work properly?plus-squaremessage-squaremessage-square2fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareAnyone get Amazon’s long-context MistralLite to work properly?plus-squaremadmax_br5@alien.topB to LocalLLaMA@poweruser.forumEnglish · 1 year agomessage-square2fedilink
madmax_br5@alien.topB to LocalLLaMA@poweruser.forumEnglish · 1 year agoBest vision model for dense OCR?plus-squaremessage-squaremessage-square1fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareBest vision model for dense OCR?plus-squaremadmax_br5@alien.topB to LocalLLaMA@poweruser.forumEnglish · 1 year agomessage-square1fedilink
I don’t know if there’s much value there when LORA’s are easily portable — you can just select the right lora as needed. One base model instance on one machine, many potential experts. This has been demonstrated.