-
Using v0.8.6, the new `--model` param throws an Error 404 with either `gpt-4` or `gpt-4-32k`, however `gpt-3.5-turbo` does function correctly.
For example:
```
sgpt --model gpt-4
╭──────────────…
-
-
I provided the key, but:
{
"error": {
"message": "You didn't provide an API key. You need to provide your API key in an Authorization header using Bearer auth (i.e. Authorization: Beare…
-
For example:
![image](https://user-images.githubusercontent.com/6214067/227720828-5de56ebd-0195-4333-866c-5bf4d30e645b.png)
I guess the root cause is chat gpt outputs extra `Command: ` prefix.
-
How do we run this from source?
Looks like the app can't find its package references:
```
(venv) me@cwgpt-s0kd:~/shell_gpt/sgpt$ python app.py
Traceback (most recent call last):
File "/home…
-
SGPT color in my shell is one of the hardest to read color, I wish I could configure this in config file.
-
It would be useful to have a -m (--model 'gpt-4') argument for sgpt
https://platform.openai.com/docs/models/gpt-4
-
I am trying to unlock the bootloader on moto tab g70(rebranded lenovo p11 plus ).
It has a Mediatek Helio G90T.
My plan is to run a degoogled version of andoid on it but I am running into major…
-
I think it would be really cool if there was an option to start `sgpt` with a loop/readline mode that continuously accepted input and automatically generated a chat identifier.
For example, you sh…
-
Seems like the [huggingface models](https://huggingface.co/Muennighoff) are all gone. Did something unfortunate happen?