I’m trying to use the groq moonshotai/kimi-k2-instruct model. According to the documentation on moonshotai/Kimi-K2-Instruct · Hugging Face this model isnt’ compatible with OpenAI or Gemini tokenizers and it appears to use it’s own custom tokenizer. Is it possible to configure discourse to use a cus…

TL;DR pick the closest tokenizer and set the maximum context to some thousands less to allow for the difference to not affect you.

Thanks. So I decided to enroll the services of ChatGPT, Gemini and Grok to help me decided which tokenizer to use; which would be the closest match to the Kimi Instruct TikToken/BPE tokenizer to generate the most accurate output from the model. I must say modern AI models are fairly representative …

Also worth noting … majority of coding agents these days don’t even bother with an accurate tokenizer like Discourse does. They just estimate at 4 letters per token. cl100k will be plenty fine for the vast majority of use cases on llms with slightly different tokenizers.

كيفية استخدام نماذج الذكاء الاصطناعي مع مُرمّزات مخصصة

الدعم

Falco (Falco) 14 ديسمبر 2025، 12:02ص 2

TL;DR اختر أقرب مُرمّز (tokenizer) واضبط السياق الأقصى (maximum context) على أقل بضعة آلاف للسماح للفارق بعدم التأثير عليك.

الموضوع		الردود	مرات العرض
Adding Semantic Search feature for our self-hosted discourse site Support ai , ai-search	9	266	19 مارس 2025
Frustrations on AI spam detector Support spam , ai	9	187	21 ديسمبر 2025
AI exceeds LLM token thresholds randomly and unpredictably Support ai	3	89	6 مايو 2026
Configuring OpenRouter language models Integrations ai	0	1172	10 ديسمبر 2024
How to implement Mistral with Embeddings Support related-topics , ai	6	255	11 مايو 2025

كيفية استخدام نماذج الذكاء الاصطناعي مع مُرمّزات مخصصة

الموضوعات ذات الصلة