The all-MiniLM-L6-v2 vs mpnet-base-v2 tradeoff is the exact decision I keep running into — 384 vs 768 dimensions sounds like a clear upgrade until you measure the latency hit on retrieval. Worth noting that for domain-specific RAG, fine-tuning a smaller model often beats the larger general-purpose one.
The all-MiniLM-L6-v2 vs mpnet-base-v2 tradeoff is the exact decision I keep running into — 384 vs 768 dimensions sounds like a clear upgrade until you measure the latency hit on retrieval. Worth noting that for domain-specific RAG, fine-tuning a smaller model often beats the larger general-purpose one.
Yes, klement completely agree.