I’m creating AI agents directly in Flowise, I can use several models in a single project. But, I have very specific and complex instructions for my agent, I realize that if I use any other model other than GPT 4, the instructions are not executed 100%, models like GPT 4 turbo or GPT 4 turbo something. But GPT 4, which always manages to perform perfectly, has token limitations, and I specifically want to use GPT 4 with 128k, is it possible? Or will I have to puzzle over my instructions to work on other models?
jr.2509
2
The context window for gpt-4 at 8,192 tokens can’t be circumvented unfortunately.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| How to use the 128k context using api | 2 | 399 | September 8, 2024 | |
| Create or customize models with more tokens | 3 | 936 | November 29, 2023 | |
| What if input token size over 128k? | 0 | 153 | June 25, 2024 | |
| Why is 128K token gpt-4 turbo not available in custom GPTs | 3 | 621 | November 29, 2023 | |
| At the end, is GPT-4-turbo 128k or 4k? | 3 | 984 | February 22, 2024 |