mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
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>
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 textwrap
|
|
|
|
from termcolor import colored
|
|
|
|
from llama_toolchain.cli.subcommand import Subcommand
|
|
|
|
|
|
class ModelTemplate(Subcommand):
|
|
"""Llama model cli for describe a model template (message formats)"""
|
|
|
|
def __init__(self, subparsers: argparse._SubParsersAction):
|
|
super().__init__()
|
|
self.parser = subparsers.add_parser(
|
|
"template",
|
|
prog="llama model template",
|
|
description="Show llama model message formats",
|
|
epilog=textwrap.dedent(
|
|
"""
|
|
Example:
|
|
llama model template <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-family",
|
|
type=str,
|
|
default="llama3_1",
|
|
help="Model Family (llama3_1, llama3_X, etc.)",
|
|
)
|
|
self.parser.add_argument(
|
|
"--name",
|
|
type=str,
|
|
help="Usecase template name (system_message, user_message, assistant_message, tool_message)...",
|
|
required=False,
|
|
)
|
|
|
|
def _run_model_template_cmd(self, args: argparse.Namespace) -> None:
|
|
from llama_models.llama3_1.api.interface import (
|
|
list_jinja_templates,
|
|
render_jinja_template,
|
|
)
|
|
from llama_toolchain.cli.table import print_table
|
|
|
|
if args.name:
|
|
template, tokens_info = render_jinja_template(args.name)
|
|
rendered = ""
|
|
for tok, is_special in tokens_info:
|
|
if is_special:
|
|
rendered += colored(tok, "yellow", attrs=["bold"])
|
|
else:
|
|
rendered += tok
|
|
rendered += "\n"
|
|
print_table(
|
|
[
|
|
("Name", colored(template.template_name, "white", attrs=["bold"])),
|
|
("Template", rendered),
|
|
("Notes", template.notes),
|
|
],
|
|
separate_rows=True,
|
|
)
|
|
else:
|
|
templates = list_jinja_templates()
|
|
headers = ["Role", "Template Name"]
|
|
print_table(
|
|
[(t.role, t.template_name) for t in templates],
|
|
headers,
|
|
)
|