TL;DR pick the closest tokenizer and set the maximum context to some thousands less to allow for the difference to not affect you.
Falco
(Falco)
2
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Adding Semantic Search feature for our self-hosted discourse site | 9 | 272 | March 19, 2025 | |
| Frustrations on AI spam detector | 8 | 187 | November 21, 2025 | |
| AI exceeds LLM token thresholds randomly and unpredictably | 3 | 102 | May 6, 2026 | |
| Configuring OpenRouter language models | 0 | 1231 | December 10, 2024 | |
| How to implement Mistral with Embeddings | 5 | 272 | April 11, 2025 |