𝐀𝐧 𝐮𝐧𝐞𝐱𝐩𝐞𝐜𝐭𝐞𝐝 𝐥𝐢𝐦𝐢𝐭𝐚𝐭𝐢𝐨𝐧: 𝐆𝐏𝐓-4 𝐡𝐚𝐬 128𝐊 𝐜𝐨𝐧𝐭𝐞𝐱𝐭 … 𝐛𝐮𝐭 𝐧𝐨𝐭 𝐪𝐮𝐢𝐭𝐞 𝐬𝐨! I am running a new experiment with GPT-4 to test the usability of its large context for the task of translation. While doing it, I kept getting a very short answer from the model when passing it a context of 60K tokens. Initially…

The GPT-4-Turbo model has a 4K token output limit, you are doing nothing wrong in that regard. The more suitable model would be GPT-4-32K, but I am unsure if that is now in general release or not. If you go to the playground https://platform.openai.com/playground?mode=chat and ensure you art in C…

GPT-4 128K only has 4096 completion tokens

API

BorgCube November 26, 2023, 3:48pm 8

Ouch! This is extremely disappointing as I’ve been awaiting a GPT 4-model with larger capacity to make my new app work…

2 Likes

Topic		Replies	Views
Chat GPT4 1106 vs ChatGPT 4: Impressive drop in quality API gpt-4 , chatgpt	27	15559	February 14, 2024
GPT 4 Turbo is limited to 4K? API gpt-4	16	14007	April 9, 2024
API \| Max Token Error \| Tier 4 \| Fluctuating between 128000 and 4096 Bugs api	3	3450	November 30, 2023
Why is gpt-3.5-turbo-1106 max_tokens limited to 4096? API	3	13960	January 11, 2024
Test new 128k window on gpt-4-1106-preview API	29	18302	February 6, 2024

GPT-4 128K only has 4096 completion tokens

Related topics