Open zululu2023 opened 1 year ago
I believe I got this working by modifying the server/config.py
orig:
models = { 'text-gpt-0040-render-sha-0': 'gpt-4', 'text-gpt-0035-render-sha-0': 'gpt-3.5-turbo', 'text-gpt-0035-render-sha-0301': 'gpt-3.5-turbo-0314', 'text-gpt-0040-render-sha-0314': 'gpt-4-0314', }
New:
models = { 'text-gpt-0040-render-sha-0': 'gpt-4', 'text-gpt-0035-render-sha-0': 'gpt-3.5-turbo', 'text-gpt-0035-render-sha-0': 'gpt-3.5-turbo-16k', 'text-gpt-0035-render-sha-0301': 'gpt-3.5-turbo-0314', 'text-gpt-0040-render-sha-0314': 'gpt-4-0314', }
Then start as normal
how to update to new gpt-4-0125-preview model?
According to OpenAI's latest policy, the token limit for gpt-3.5-turbo has been increased from 4,000 tokens to a maximum of 16,000 tokens for the gpt-3.5-turbo-16k model. In our current files, we need to make the corresponding parameter adjustments. Could you please let me know which specific files and code you are referring to so that I can provide you with the necessary instructions? Thank you!