| ▲ | thellimist 8 hours ago | |
What do you mean? | ||
| ▲ | hiccuphippo 7 hours ago | parent [-] | |
The article says the LLM has to load 15540 tokens every time, I wonder if that can be reduced while retaining the context maybe with deduplications, removing superfluous words, using shorter expressions with the same meaning or things like that. | ||