Unverified50% confidenceFactExact time
The classic BGE versions (such as bge-large-zh) have an input limit of 512 tokens.
1
Sources
50%
Confidence
Long-term
Relevance
10/23/2026
First Seen
Sources
One Diary Gives AI Persistent Memory: A Semantic Retrieval Solution Tested
bilibiliClaude-其实是鱼别揭穿10/22/2026
Related Entities
Related Claims
Unverifiedbge-small is the small-size version in the BGE series of sentence embedding models released by BAAI, with roughly tens of millions of parameters, and outputs 384-dimensional vectors.65% similarUnverified生产中典型做法是先用向量检索和BM25快速召回50-100个候选结果，再用reranker精排取top-k送入LLM58% similarVerifiedThe core mechanism of BM25 is based on three factors: term frequency (TF), inverse document frequency (IDF), and document length normalization, with parameter k1 typically set between 1.2 and 2.0 and b typically set at 0.75.58% similarUnverifiedBLE (Bluetooth Low Energy) is the low-power subset introduced in the Bluetooth 4.0 specification, with a peak power consumption of approximately one-tenth that of classic Bluetooth.56% similarUnverifiedLFM2.5-24B-A2B has 24 billion total parameters and uses an MoE architecture with 64 experts per block, Top-4 dynamic routing, and only 2.45 billion parameters activated per token.54% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1088501API
curl https://kongchang.com/api/v1/knowledge/claims/1088501MCP
get_claim(id=1088501)