Verified70% confidenceFactExact time
Microsoft's Phi series models (Phi-1, Phi-1.5, Phi-2), with parameter counts ranging from 1.3B to 2.7B, are trained on high-quality synthetic data generated by GPT-4 and approach or surpass models with 10 times the parameters on multiple benchmarks.
4
Sources
70%
Confidence
Long-term
Relevance
7/23/2026
First Seen
Sources
Related Claims
UnverifiedA foundation model refers to a general-purpose model pre-trained on large-scale data that can support a variety of downstream tasks, with typical examples including the GPT series and multimodal models such as CLIP and GPT-4V.73% similarUnverifiedStanford's Alpaca project used GPT-3.5 to generate 52K instruction data points for training a 7B-parameter LLaMA.71% similarVerifiedMainstream large language models (including GPT-4, DeepSeek, Claude, etc.) are all trained on static corpora and have a definitive knowledge cutoff date.71% similarUnverified生成式AI是基于大规模预训练语言模型（LLM）的技术范式，代表产品包括GPT-4、Claude、Gemini71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/597533API
curl https://kongchang.com/api/v1/knowledge/claims/597533MCP
get_claim(id=597533)