dleemiller

/

sts-bert-hash-nano

like 0

Have I interpreted this appropriately, does this mean that this model should have a context length of 8192?

Extended context length: Processes sequences up to 8192 tokens, great for LLM output evals.

The reason why I am confused is that the config.json set the following.
"max_position_embeddings": 512,

this seems contradictory.