Unverified60% confidenceBenchmarkExact time
After 15 training epochs on the demonstration dataset, the text classification model achieves an accuracy of 99%, with a total of 110,000 model parameters (16,000 for Attention, 33,000 for FFN, and the remainder for Embedding)
2
Sources
60%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe model is trained in two stages: first masked language model pre-training on about 20 million sentences from FineWeb-Edu, then correction fine-tuning on 12.02 million (noisy, clean) pairs, of which 30% are identity pairs.77% similarUnverifiedThe example model in the article has approximately 110,000 total parameters, with the Attention module accounting for 16,000 and the FFN accounting for 33,000.75% similarUnverifiedIn the strictly comparable experiment with fifteen players and three impostors in the sixth league, the trained network's crew win rate over 300 rounds was 93.3%, while gpt-oss under the dialogue+intuition format won 16 of 20 rounds (80%), with a one-sided Fisher exact test p = 0.052.71% similarUnverified参数量在1亿以下的轻量模型经领域数据微调后可达95%以上意图分类准确率，单次推理延迟控制在5-20ms以内71% similarUnverifiedSizing backfill by fact count is a poor approximation, since model cost is a function of text; batches began to be limited by text volume, capped at about 8000 characters; a full backfill of about 524 facts was estimated at 3.4 minutes, completed in about 19 batches.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/904293API
curl https://kongchang.com/api/v1/knowledge/claims/904293MCP
get_claim(id=904293)