forked from phoenix-oss/llama-stack-mirror
314ee09ae3
llama-models should have extremely minimal cruft. Its sole purpose should be didactic -- show the simplest implementation of the llama models and document the prompt formats, etc. This PR is the complement to https://github.com/meta-llama/llama-models/pull/279 ## Test Plan Ensure all `llama` CLI `model` sub-commands work: ```bash llama model list llama model download --model-id ... llama model prompt-format -m ... ``` Ran tests: ```bash cd tests/client-sdk LLAMA_STACK_CONFIG=fireworks pytest -s -v inference/ LLAMA_STACK_CONFIG=fireworks pytest -s -v vector_io/ LLAMA_STACK_CONFIG=fireworks pytest -s -v agents/ ``` Create a fresh venv `uv venv && source .venv/bin/activate` and run `llama stack build --template fireworks --image-type venv` followed by `llama stack run together --image-type venv` <-- the server runs Also checked that the OpenAPI generator can run and there is no change in the generated files as a result. ```bash cd docs/openapi_generator sh run_openapi_generator.sh ```
81 lines
2.7 KiB
Python
81 lines
2.7 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 termcolor import colored
|
|
|
|
from llama_stack.cli.subcommand import Subcommand
|
|
from llama_stack.cli.table import print_table
|
|
from llama_stack.models.llama.sku_list import resolve_model
|
|
|
|
|
|
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,
|
|
help="See `llama model list` or `llama model list --show-all` for the list of available models",
|
|
)
|
|
|
|
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,
|
|
)
|