forked from phoenix-oss/llama-stack-mirror
47fccf0d03
# What does this PR do? [Provide a short summary of what this PR does and why. Link to relevant issues if applicable.] Since the subcommands used `MODEL_ID`, it would be better to use it in `model list` and make it easy to find it. ``` $ llama model verify-download --help usage: llama model verify-download [-h] --model-id MODEL_ID << $ llama model describe --help usage: llama model describe [-h] -m MODEL_ID << $ llama download --help --model-id MODEL_ID See `llama model list` or `llama model list --show-all` for the list of available models before: $ llama model list +-----------------------------------------+-----------------------------------------------------+----------------+ | Model Descriptor | Hugging Face Repo | Context Length | +-----------------------------------------+-----------------------------------------------------+----------------+ after: $ llama model list +-----------------------------------------+-----------------------------------------------------+----------------+ | Model Descriptor | Model ID | Context Length | +-----------------------------------------+-----------------------------------------------------+----------------+ | Llama3.1-8B | meta-llama/Llama-3.1-8B | 128K | +-----------------------------------------+-----------------------------------------------------+----------------+ ``` [//]: # (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>
62 lines
1.8 KiB
Python
62 lines
1.8 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
|
|
|
|
from llama_models.sku_list import all_registered_models
|
|
|
|
from llama_stack.cli.subcommand import Subcommand
|
|
from llama_stack.cli.table import print_table
|
|
|
|
|
|
class ModelList(Subcommand):
|
|
"""List available llama models"""
|
|
|
|
def __init__(self, subparsers: argparse._SubParsersAction):
|
|
super().__init__()
|
|
self.parser = subparsers.add_parser(
|
|
"list",
|
|
prog="llama model list",
|
|
description="Show available llama models",
|
|
formatter_class=argparse.RawTextHelpFormatter,
|
|
)
|
|
self._add_arguments()
|
|
self.parser.set_defaults(func=self._run_model_list_cmd)
|
|
|
|
def _add_arguments(self):
|
|
self.parser.add_argument(
|
|
"--show-all",
|
|
action="store_true",
|
|
help="Show all models (not just defaults)",
|
|
)
|
|
|
|
def _run_model_list_cmd(self, args: argparse.Namespace) -> None:
|
|
from .safety_models import prompt_guard_model_sku
|
|
|
|
headers = [
|
|
"Model Descriptor",
|
|
"Model ID",
|
|
"Context Length",
|
|
]
|
|
|
|
rows = []
|
|
for model in all_registered_models() + [prompt_guard_model_sku()]:
|
|
if not args.show_all and not model.is_featured:
|
|
continue
|
|
|
|
descriptor = model.descriptor()
|
|
rows.append(
|
|
[
|
|
descriptor,
|
|
model.huggingface_repo,
|
|
f"{model.max_seq_length // 1024}K",
|
|
]
|
|
)
|
|
print_table(
|
|
rows,
|
|
headers,
|
|
separate_rows=True,
|
|
)
|