Unverified50% confidenceFactExact time
For training acceleration, MiniDog introduces iREPA and the EUPE perceptual encoder.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedTechniques such as mixed-precision training and gradient accumulation enable training of larger models under limited GPU memory.61% similarUnverifiedMiniMind covers the complete pipeline including Tokenizer training, pre-training, supervised fine-tuning (SFT), LoRA fine-tuning, DPO reinforcement learning, and model distillation.61% similarUnverifiedAccelerated LoRA is optimized during training for a specific sampler scheduling strategy and model weights; when the actual sampler's step size distribution, noise schedule, or model quantization method is inconsistent with the training conditions, the shortcut paths learned by the LoRA may fail entirely.61% similarUnverifiedUnder the linear probing setting, SPERA achieves excellent performance by training only a small number of downstream parameters.60% similarUnverifiedThe pretraining and fine-tuning paradigm originated from NLP and computer vision, with its core being large-scale data pretraining to learn general low-level features, and downstream tasks adapted using a small amount of labeled data.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1026757API
curl https://kongchang.com/api/v1/knowledge/claims/1026757MCP
get_claim(id=1026757)