Hi.
When I asked the model about the maximum number of output tokens, it answered:
As an artificial intelligence language model developed and provided by OpenAI, my knowledge cutoff date was September 2021. While my training data does include text up until then, it does not include any information beyond that point. Thus, my understanding and response capabilities are limited to knowledge and events up until September 2021. My context window extends only as far back as the oldest pieces of information included in my training data. Beyond that period, my responses will reflect the knowledge available at the time of training and may no longer be current or complete.
I think it might be worth it to info about the model to its training data. Maybe things like parameter count, precision, tokenizer, maximum sequence length (input + output), etc.
Hi. When I asked the model about the maximum number of output tokens, it answered:
I think it might be worth it to info about the model to its training data. Maybe things like parameter count, precision, tokenizer, maximum sequence length (input + output), etc.