Embedding Model Determinism, big difference

[_j]

Yes, I explained where the AI analysis started. Your “sig-figs” are over-concerned.

Models have been non-deterministic for two years, since gpt-3.5-“turbo”.

However, the output is entirely suitable for any embeddings application needing semantic search.

Feature Request: Deterministic Answer Option for Unit Testing

I have investigated the problem that causes non-determinism. The source or root is with the model vectors and logits produced. Their significant figure changes between runs are similar to embeddings. When the values of likelihood of a token appearing every run continuously change by up to several percent, the top-ranking probability that comes from the language model can change. Here, as part of my investigation with many different styles of API calls and scripts to process the data returned, …