mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
# What does this PR do?
[Provide a short summary of what this PR does and why. Link to relevant
issues if applicable.]
19ae4b35d9/llama_stack/cli/model/prompt_format.py (L47)
Based on the comment: `Only Llama 3.1 and 3.2 are supported`, even 3.1,
3.2 are not all models can show it with `prompt-format`, so cannot refer
to `llama model list`,
only refer to list when enter a invalid model, so it would be nice to
help to check the valid models:
```
llama model prompt-format -m Llama3.1-405B-Instruct:bf16-mp8
usage: llama model prompt-format [-h] [-m MODEL_NAME] [-l]
llama model prompt-format: error: Llama3.1-405B-Instruct:bf16-mp8 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
before:
$ llama model prompt-format --help
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>
after:
$ llama model prompt-format --help
usage: llama model prompt-format [-h] [-m MODEL_NAME] [-l]
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.)
-l, --list List the valid supported models
Example:
llama model prompt-format <options>
$ llama model prompt-format -l
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ Model ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
│ 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 │
└──────────────────────────────┘
```
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
[Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.*]
[//]: # (## Documentation)
---------
Signed-off-by: reidliu <reid201711@gmail.com>
Co-authored-by: reidliu <reid201711@gmail.com>
119 lines
4.2 KiB
Python
119 lines
4.2 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
import argparse
|
|
import textwrap
|
|
from io import StringIO
|
|
|
|
from llama_stack.cli.subcommand import Subcommand
|
|
from llama_stack.cli.table import print_table
|
|
from llama_stack.models.llama.datatypes import CoreModelId, ModelFamily, is_multimodal, model_family
|
|
|
|
|
|
class ModelPromptFormat(Subcommand):
|
|
"""Llama model cli for describe a model prompt format (message formats)"""
|
|
|
|
def __init__(self, subparsers: argparse._SubParsersAction):
|
|
super().__init__()
|
|
self.parser = subparsers.add_parser(
|
|
"prompt-format",
|
|
prog="llama model prompt-format",
|
|
description="Show llama model message formats",
|
|
epilog=textwrap.dedent(
|
|
"""
|
|
Example:
|
|
llama model prompt-format <options>
|
|
"""
|
|
),
|
|
formatter_class=argparse.RawTextHelpFormatter,
|
|
)
|
|
self._add_arguments()
|
|
self.parser.set_defaults(func=self._run_model_template_cmd)
|
|
|
|
def _add_arguments(self):
|
|
self.parser.add_argument(
|
|
"-m",
|
|
"--model-name",
|
|
type=str,
|
|
default="llama3_1",
|
|
help="Model Family (llama3_1, llama3_X, etc.)",
|
|
)
|
|
|
|
def _run_model_template_cmd(self, args: argparse.Namespace) -> None:
|
|
import importlib.resources
|
|
|
|
# Only Llama 3.1 and 3.2 are supported
|
|
supported_model_ids = [
|
|
m for m in CoreModelId if model_family(m) in {ModelFamily.llama3_1, ModelFamily.llama3_2}
|
|
]
|
|
|
|
model_list = [m.value for m in supported_model_ids]
|
|
model_str = "\n".join(model_list)
|
|
|
|
if args.list:
|
|
headers = ["Model(s)"]
|
|
rows = []
|
|
for m in model_list:
|
|
rows.append(
|
|
[
|
|
m,
|
|
]
|
|
)
|
|
print_table(
|
|
rows,
|
|
headers,
|
|
separate_rows=True,
|
|
)
|
|
return
|
|
|
|
try:
|
|
model_id = CoreModelId(args.model_name)
|
|
except ValueError:
|
|
self.parser.error(f"{args.model_name} is not a valid Model. Choose one from --\n{model_str}")
|
|
|
|
if model_id not in supported_model_ids:
|
|
self.parser.error(f"{model_id} is not a valid Model. Choose one from --\n {model_str}")
|
|
|
|
llama_3_1_file = importlib.resources.files("llama_models") / "llama3_1/prompt_format.md"
|
|
llama_3_2_text_file = importlib.resources.files("llama_models") / "llama3_2/text_prompt_format.md"
|
|
llama_3_2_vision_file = importlib.resources.files("llama_models") / "llama3_2/vision_prompt_format.md"
|
|
if model_family(model_id) == ModelFamily.llama3_1:
|
|
with importlib.resources.as_file(llama_3_1_file) as f:
|
|
content = f.open("r").read()
|
|
elif model_family(model_id) == ModelFamily.llama3_2:
|
|
if is_multimodal(model_id):
|
|
with importlib.resources.as_file(llama_3_2_vision_file) as f:
|
|
content = f.open("r").read()
|
|
else:
|
|
with importlib.resources.as_file(llama_3_2_text_file) as f:
|
|
content = f.open("r").read()
|
|
|
|
render_markdown_to_pager(content)
|
|
|
|
|
|
def render_markdown_to_pager(markdown_content: str):
|
|
from rich.console import Console
|
|
from rich.markdown import Markdown
|
|
from rich.style import Style
|
|
from rich.text import Text
|
|
|
|
class LeftAlignedHeaderMarkdown(Markdown):
|
|
def parse_header(self, token):
|
|
level = token.type.count("h")
|
|
content = Text(token.content)
|
|
header_style = Style(color="bright_blue", bold=True)
|
|
header = Text(f"{'#' * level} ", style=header_style) + content
|
|
self.add_text(header)
|
|
|
|
# Render the Markdown
|
|
md = LeftAlignedHeaderMarkdown(markdown_content)
|
|
|
|
# Capture the rendered output
|
|
output = StringIO()
|
|
console = Console(file=output, force_terminal=True, width=100) # Set a fixed width
|
|
console.print(md)
|
|
rendered_content = output.getvalue()
|
|
print(rendered_content)
|