Unverified50% confidenceFactExact time
The source does not provide quantitative benchmark comparisons for VKORE-46M-NPU, including perplexity scores, downstream task accuracy, and training throughput in tokens per second.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/15/2026
First Seen
Valid until: 10/29/2026
Sources
Related Entities
Related Claims
UnverifiedVKORE-46M-NPU has a parameter scale of 46M, about one-third of GPT-2 Small (about 124 million parameters), and its significance lies in validating that the NPU training path is feasible, rather than in the quality of the model itself.78% similarUnverifiedIn a needle-in-a-haystack experiment with a 128K Token context and about 16,000 key-value pairs, changing the position of just one key-value pair produced a maximum accuracy gap of 40.2% for DeepSeek-V4-Flash-Base, 34.8% for DeepSeek-V4-Pro-Base, and still 19.1% and 14.8% respectively after post-training optimization.68% similarUnverifiedWhen DINOv3 ViT-H+/16 is pruned to 50% sparsity, removing 427 million parameters, ImageNet-1k linear probe accuracy drops by only 0.8%, without weight correction or retraining.66% similarUnverifiedThe Label-Only method achieves an accuracy of 0.896 and a span F1 of 0.564, with verbatim citation improving from 0.597 before training to 0.729.65% similarUnverifiedVKORE and PyTorch achieve a numerical consistency of 0.9999 in LoRA training.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1041058API
curl https://kongchang.com/api/v1/knowledge/claims/1041058MCP
get_claim(id=1041058)