forked from phoenix-oss/llama-stack-mirror
e830814399
* Add distribution CLI scaffolding * More progress towards `llama distribution install` * getting closer to a distro definition, distro install + configure works * Distribution server now functioning * read existing configuration, save enums properly * Remove inference uvicorn server entrypoint and llama inference CLI command * updated dependency and client model name * Improved exception handling * local imports for faster cli * undo a typo, add a passthrough distribution * implement full-passthrough in the server * add safety adapters, configuration handling, server + clients * cleanup, moving stuff to common, nuke utils * Add a Path() wrapper at the earliest place * fixes * Bring agentic system api to toolchain Add adapter dependencies and resolve adapters using a topological sort * refactor to reduce size of `agentic_system` * move straggler files and fix some important existing bugs * ApiSurface -> Api * refactor a method out * Adapter -> Provider * Make each inference provider into its own subdirectory * installation fixes * Rename Distribution -> DistributionSpec, simplify RemoteProviders * dict key instead of attr * update inference config to take model and not model_dir * Fix passthrough streaming, send headers properly not part of body :facepalm * update safety to use model sku ids and not model dirs * Update cli_reference.md * minor fixes * add DistributionConfig, fix a bug in model download * Make install + start scripts do proper configuration automatically * Update CLI_reference * Nuke fp8_requirements, fold fbgemm into common requirements * Update README, add newline between API surface configurations * Refactor download functionality out of the Command so can be reused * Add `llama model download` alias for `llama download` * Show message about checksum file so users can check themselves * Simpler intro statements * get ollama working * Reduce a bunch of dependencies from toolchain Some improvements to the distribution install script * Avoid using `conda run` since it buffers everything * update dependencies and rely on LLAMA_TOOLCHAIN_DIR for dev purposes * add validation for configuration input * resort imports * make optional subclasses default to yes for configuration * Remove additional_pip_packages; move deps to providers * for inline make 8b model the default * Add scripts to MANIFEST * allow installing from test.pypi.org * Fix #2 to help with testing packages * Must install llama-models at that same version first * fix PIP_ARGS --------- Co-authored-by: Hardik Shah <hjshah@fb.com> Co-authored-by: Hardik Shah <hjshah@meta.com>
75 lines
2.4 KiB
Python
75 lines
2.4 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_toolchain.cli.subcommand import Subcommand
|
|
from llama_toolchain.cli.table import print_table
|
|
from llama_toolchain.common.serialize import EnumEncoder
|
|
|
|
|
|
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:
|
|
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"]),
|
|
),
|
|
("HuggingFace ID", model.huggingface_repo or "<Not Available>"),
|
|
("Description", model.description_markdown),
|
|
("Context Length", f"{model.max_seq_length // 1024}K tokens"),
|
|
("Weights format", model.quantization_format.value),
|
|
("Model params.json", json.dumps(model.model_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, cls=EnumEncoder, indent=4),
|
|
)
|
|
)
|
|
|
|
print_table(
|
|
rows,
|
|
separate_rows=True,
|
|
)
|