The GPT-2 model used r50k_base: vocab size = 50k
The GPT-3 model used r50k_base: vocab size = 50k
The GPT-3.5 model used cl100k_base: vocab size = 100k
The GPT-4 model used cl100k_base: vocab size = 100k
Get Ṁ1,000 play money
Related questions
When will OpenAI release a more capable LLM?
Will OpenAI have the best LLM in 2024?
63% chance
Will OpenAI release a tokenizer with vocab size > 150k by end of 2024?
42% chance
Will OpenAI release a tokenizer with more than 210000 tokens before 2026?
24% chance
Will the next LLM released by OpenAI be worse than GPT-4 at MMLU?
19% chance
Sort by:
@firstuserhere So YES if there's a GPT-4.5/5 that uses a tokeniser not on this list, and NO if there's a GPT-4.5/5 that uses a tokeniser that is on this list?
Related questions
Related questions
When will OpenAI release a more capable LLM?
Will Google have a better LLM than OpenAI by 2025?
36% chance
Will OpenAI have the best LLM in 2024?
63% chance
Will there be a OpenAI LLM known as GPT-4.5? by 2033
35% chance
Will OpenAI release a tokenizer with vocab size > 150k by end of 2024?
42% chance
Will future OpenAI LLMs be called GPT-n?
65% chance
Will OpenAI release a tokenizer with more than 210000 tokens before 2026?
24% chance
Will OpenAI reveal a textless LLM before 2025?
26% chance
Will the next LLM released by OpenAI be worse than GPT-4 at MMLU?
19% chance
What is the next OpenAI LLM logo color?