Unverified50% confidenceFactExact time
Once a tokenizer is trained it is fixed, and model training and inference must use the same tokenizer; otherwise the correspondence between tokens and model parameters would be broken.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedTransformer 架构的模型参数在训练完成后即被固定，除非进行微调或持续预训练否则无法获取新知识71% similarUnverified更换Tokenizer意味着需要重新训练整个模型，因为嵌入层的维度与词表大小直接挂钩71% similarUnverifiedDuring fine-tuning, model weights, gradients, and optimizer states must be stored simultaneously, making VRAM consumption typically 3–4 times that of inference.68% similarUnverified对抗图案通常针对特定模型、特定版本训练，更换检测算法或升级模型权重后可能完全失效67% similarUnverifiedA model's core parameter weights are fixed after training is complete; even when new information is obtained through external tools, the model still relies on the worldview formed during training when making integrated judgments.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1067373API
curl https://kongchang.com/api/v1/knowledge/claims/1067373MCP
get_claim(id=1067373)