llama-stack/llama_stack
Alina Ryan c02464b635
fix: Clarify llama model prompt-format help text (#1010)
# What does this PR do?
Updates the help text for the `llama model prompt-format` command to
clarify that users should provide a specific model name (e.g.,
Llama3.1-8B, Llama3.2-11B-Vision), not a model family. Removes the
default value and field for `--model-name` to prevent users from
mistakenly thinking a model family name is acceptable. Adds guidance to
run `llama model list` to view valid model names.

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan

Output of `llama model prompt-format -h` Before:
```
(venv) alina@fedora:~/dev/llama/llama-stack$ llama model prompt-format -h
usage: llama model prompt-format [-h] [-m MODEL_NAME]

Show llama model message formats

options:
  -h, --help            show this help message and exit
  -m MODEL_NAME, --model-name MODEL_NAME
                        Model Family (llama3_1, llama3_X, etc.)

Example:
    llama model prompt-format <options>
(venv) alina@fedora:~/dev/llama/llama-stack$ llama model prompt-format --model-name llama3_1
usage: llama model prompt-format [-h] [-m MODEL_NAME]
llama model prompt-format: error: llama3_1 is not a valid Model. Choose one from --
Llama3.1-8B
Llama3.1-70B
Llama3.1-405B
Llama3.1-8B-Instruct
Llama3.1-70B-Instruct
Llama3.1-405B-Instruct
Llama3.2-1B
Llama3.2-3B
Llama3.2-1B-Instruct
Llama3.2-3B-Instruct
Llama3.2-11B-Vision
Llama3.2-90B-Vision
Llama3.2-11B-Vision-Instruct
Llama3.2-90B-Vision-Instruct
```

Output of `llama model prompt-format -h` After:
```
(venv) alina@fedora:~/dev/llama/llama-stack$ llama model prompt-format -h
usage: llama model prompt-format [-h] [-m MODEL_NAME]

Show llama model message formats

options:
  -h, --help            show this help message and exit
  -m MODEL_NAME, --model-name MODEL_NAME
                        Example: Llama3.1-8B or Llama3.2-11B-Vision, etc
                        (Run `llama model list` to see a list of valid model names)

Example:
    llama model prompt-format <options>

```

Signed-off-by: Alina Ryan <aliryan@redhat.com>
2025-03-13 20:47:09 -04:00
..
apis feat: add provider API for listing and inspecting provider info (#1429) 2025-03-13 15:07:21 -07:00
cli fix: Clarify llama model prompt-format help text (#1010) 2025-03-13 20:47:09 -04:00
distribution feat: add provider API for listing and inspecting provider info (#1429) 2025-03-13 15:07:21 -07:00
models/llama refactor: move all datetime.now() calls to UTC (#1589) 2025-03-13 15:34:53 -07:00
providers refactor: move all datetime.now() calls to UTC (#1589) 2025-03-13 15:34:53 -07:00
scripts refactor(test): introduce --stack-config and simplify options (#1404) 2025-03-05 17:02:02 -08:00
strong_typing Ensure that deprecations for fields follow through to OpenAPI 2025-02-19 13:54:04 -08:00
templates fix: passthrough provider template + fix (#1612) 2025-03-13 09:44:26 -07:00
__init__.py export LibraryClient 2024-12-13 12:08:00 -08:00
env.py refactor(test): move tools, evals, datasetio, scoring and post training tests (#1401) 2025-03-04 14:53:47 -08:00
log.py fix: respect log_level in uvicorn and third party libs (#1524) 2025-03-12 11:07:28 -07:00
schema_utils.py ci: add mypy for static type checking (#1101) 2025-02-21 13:15:40 -08:00