pepperfree@sh.itjust.works to LocalLLaMA@sh.itjust.worksEnglish · 10 days agoWhen DeepSeek V4 and R2?sh.itjust.worksexternal-linkmessage-square26fedilinkarrow-up1191arrow-down16
arrow-up1185arrow-down1external-linkWhen DeepSeek V4 and R2?sh.itjust.workspepperfree@sh.itjust.works to LocalLLaMA@sh.itjust.worksEnglish · 10 days agomessage-square26fedilink
minus-squareveroxii@aussie.zonelinkfedilinkEnglisharrow-up5·10 days agoOr maybe Facebook data is even worse than Twitter?
minus-squarepepperfree@sh.itjust.worksOPlinkfedilinkEnglisharrow-up1arrow-down1·10 days agoLlama 3.3 was good, tho. For the multimodal, llama 4 also use llama3.2 approach where the image and text is made into single model instead using CLIP or siglip.
Or maybe Facebook data is even worse than Twitter?
Llama 3.3 was good, tho. For the multimodal, llama 4 also use llama3.2 approach where the image and text is made into single model instead using CLIP or siglip.