mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
4e76d312fa
# What does this PR do? [Provide a short summary of what this PR does and why. Link to relevant issues if applicable.] Re-check and based on the doc, the download model id, actually is model descriptor(also without `meta-llama/`). https://llama-stack.readthedocs.io/en/latest/references/llama_cli_reference/index.html ``` $ llama download --source huggingface --model-id Llama-Guard-3-1B:int4 --hf-token xxx # model descriptor Fetching 8 files: 0%| | 0/8 [00:00<?, ?it/s] LICENSE.txt: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 7.71k/7.71k [00:00<00:00, 10.5MB/s] $ llama download --source huggingface --model-id Llama-Guard-3-1B-INT4 --hf-token xxxx # hugging face repo without meta-llama/ usage: llama download [-h] [--source {meta,huggingface}] [--model-id MODEL_ID] [--hf-token HF_TOKEN] [--meta-url META_URL] [--max-parallel MAX_PARALLEL] [--ignore-patterns IGNORE_PATTERNS] [--manifest-file MANIFEST_FILE] llama download: error: Model Llama-Guard-3-1B-INT4 not found <<<<--- $ llama download --source meta --model-id Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8 usage: llama download [-h] [--source {meta,huggingface}] [--model-id MODEL_ID] [--hf-token HF_TOKEN] [--meta-url META_URL] [--max-parallel MAX_PARALLEL] [--ignore-patterns IGNORE_PATTERNS] [--manifest-file MANIFEST_FILE] llama download: error: Model Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8 not found $ llama download --source meta --model-id Llama3.2-3B-Instruct:int4-spinquant-eo8 Please provide the signed URL for model Llama3.2-3B-Instruct:int4-spinquant-eo8 you received via email after visiting https://www.llama.com/llama-downloads/ (e.g., https://llama3-1.llamameta.net/*?Policy...): ^CTraceback (most recent call last): $ llama download --source meta --model-id meta-llama/Llama3.2-3B-Instruct:int4-spinquant-eo8 usage: llama download [-h] [--source {meta,huggingface}] [--model-id MODEL_ID] [--hf-token HF_TOKEN] [--meta-url META_URL] [--max-parallel MAX_PARALLEL] [--ignore-patterns IGNORE_PATTERNS] [--manifest-file MANIFEST_FILE] llama download: error: Model meta-llama/Llama3.2-3B-Instruct:int4-spinquant-eo8 not found ``` [//]: # (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>
61 lines
1.8 KiB
Python
61 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_stack.cli.subcommand import Subcommand
|
|
from llama_stack.cli.table import print_table
|
|
from llama_stack.models.llama.sku_list import all_registered_models
|
|
|
|
|
|
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(ID)",
|
|
"Hugging Face Repo",
|
|
"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,
|
|
)
|