mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
e4a1579e63
# What does this PR do? - Configured ruff linter to automatically fix import sorting issues. - Set --exit-non-zero-on-fix to ensure non-zero exit code when fixes are applied. - Enabled the 'I' selection to focus on import-related linting rules. - Ran the linter, and formatted all codebase imports accordingly. - Removed the black dep from the "dev" group since we use ruff Signed-off-by: Sébastien Han <seb@redhat.com> [//]: # (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) [//]: # (- [ ] Added a Changelog entry if the change is significant) Signed-off-by: Sébastien Han <seb@redhat.com>
80 lines
2.6 KiB
Python
80 lines
2.6 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 json
|
|
|
|
from llama_models.sku_list import resolve_model
|
|
from termcolor import colored
|
|
|
|
from llama_stack.cli.subcommand import Subcommand
|
|
from llama_stack.cli.table import print_table
|
|
|
|
|
|
class ModelDescribe(Subcommand):
|
|
"""Show details about a model"""
|
|
|
|
def __init__(self, subparsers: argparse._SubParsersAction):
|
|
super().__init__()
|
|
self.parser = subparsers.add_parser(
|
|
"describe",
|
|
prog="llama model describe",
|
|
description="Show details about a llama model",
|
|
formatter_class=argparse.RawTextHelpFormatter,
|
|
)
|
|
self._add_arguments()
|
|
self.parser.set_defaults(func=self._run_model_describe_cmd)
|
|
|
|
def _add_arguments(self):
|
|
self.parser.add_argument(
|
|
"-m",
|
|
"--model-id",
|
|
type=str,
|
|
required=True,
|
|
)
|
|
|
|
def _run_model_describe_cmd(self, args: argparse.Namespace) -> None:
|
|
from .safety_models import prompt_guard_model_sku
|
|
|
|
prompt_guard = prompt_guard_model_sku()
|
|
if args.model_id == prompt_guard.model_id:
|
|
model = prompt_guard
|
|
else:
|
|
model = resolve_model(args.model_id)
|
|
|
|
if model is None:
|
|
self.parser.error(
|
|
f"Model {args.model_id} not found; try 'llama model list' for a list of available models."
|
|
)
|
|
return
|
|
|
|
rows = [
|
|
(
|
|
colored("Model", "white", attrs=["bold"]),
|
|
colored(model.descriptor(), "white", attrs=["bold"]),
|
|
),
|
|
("Hugging Face ID", model.huggingface_repo or "<Not Available>"),
|
|
("Description", model.description),
|
|
("Context Length", f"{model.max_seq_length // 1024}K tokens"),
|
|
("Weights format", model.quantization_format.value),
|
|
("Model params.json", json.dumps(model.arch_args, indent=4)),
|
|
]
|
|
|
|
if model.recommended_sampling_params is not None:
|
|
sampling_params = model.recommended_sampling_params.dict()
|
|
for k in ("max_tokens", "repetition_penalty"):
|
|
del sampling_params[k]
|
|
rows.append(
|
|
(
|
|
"Recommended sampling params",
|
|
json.dumps(sampling_params, indent=4),
|
|
)
|
|
)
|
|
|
|
print_table(
|
|
rows,
|
|
separate_rows=True,
|
|
)
|