Unverified50% confidenceEventExact time
VIDRAFT released a small language model named VKORE-46M-NPU with 46 million parameters, pretrained entirely from random weights, and the training process did not use any GPU.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedMiniCPM5-2B open-sourced its training data, including approximately 500,000 agent samples and over 80,000 reinforcement learning samples.67% similarUnverifiedA hybrid approach is feasible: use NeMo during the training phase to optimize GPU utilization, then switch to a general-purpose inference engine such as vLLM during the deployment phase after exporting standard-format weights.67% similarUnverifiedFor a small dataset of 5,600 images, training a standard DETR from scratch is almost certain to fail, and it is recommended to load COCO pretrained weights for fine-tuning.67% similarUnverifiedLoRA fine-tuning is a roadmap item for the VKORE software layer, alongside inference acceleration and pretraining, and there is currently no public timeline.65% similarUnverified大语言模型训练通常能达到40%–60%的MFU，而朴素RL训练的MFU往往不足5%65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1032390API
curl https://kongchang.com/api/v1/knowledge/claims/1032390MCP
get_claim(id=1032390)