Hopiu/llm
1
0
Fork 0
mirror of https://github.com/Hopiu/llm.git synced 2026-03-17 05:00:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update help for GPT-4o, closes #490

Browse source
This commit is contained in:
Simon Willison 2024-05-13 12:53:31 -07:00
parent 73bbbec372
commit 8171c9a6bf
2 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/openai-models.md
View file

@ -44,7 +44,7 @@ OpenAI Completion: gpt-3.5-turbo-instruct (aliases: 3.5-instruct, chatgpt-instru
See [the OpenAI models documentation](https://platform.openai.com/docs/models) for details of each of these.
The best balance of price and capacity are the `-turbo` models. `gpt-3.5-turbo` (aliased to `3.5`) is the least expensive. `gpt-4-turbo-preview` (aliased to `4t`) is the cheapest of the GPT-4 models.
`gpt-3.5-turbo` (aliased to `3.5`) is the least expensive model. `gpt-4o` (aliased to `4o`) is the newest, cheapest and fastest of the GPT-4 family of models.
The `gpt-3.5-turbo-instruct` model is a little different - it is a completion model rather than a chat model, described in [the OpenAI completions documentation](https://platform.openai.com/docs/api-reference/completions/create).

6
docs/usage.md
View file

@ -18,9 +18,9 @@ To disable streaming and only return the response once it has completed:
```bash
llm 'Ten names for cheesecakes' --no-stream
```
To switch from ChatGPT 3.5 (the default) to GPT-4 Turbo:
To switch from ChatGPT 3.5 (the default) to GPT-4o:
```bash
llm 'Ten names for cheesecakes' -m gpt-4-turbo
llm 'Ten names for cheesecakes' -m gpt-4o
```
You can use `-m 4t` as an even shorter shortcut.
@ -361,6 +361,6 @@ OpenAI Completion: gpt-3.5-turbo-instruct (aliases: 3.5-instruct, chatgpt-instru
When running a prompt you can pass the full model name or any of the aliases to the `-m/--model` option:
```bash
llm -m chatgpt-16k \
llm -m 4o \
'As many names for cheesecakes as you can think of, with detailed descriptions'
```