phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

feat: add api.llama provider, llama-guard-4 model (#2058)

Browse source 
This PR adds a llama-stack inference provider for `api.llama.com`, as
well as adds entries for Llama-Guard-4 and updated Prompt-Guard models.
This commit is contained in:
Ashwin Bharambe 2025-04-29 10:07:41 -07:00 • committed by GitHub
parent 934446ddb4
commit 4d0bfbf984
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
21 changed files with 1526 additions and 47 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama_stack/cli/download.py
View file

@ -460,15 +460,17 @@ def run_download_cmd(args: argparse.Namespace, parser: argparse.ArgumentParser):
from llama_stack.models.llama.sku_list import llama_meta_net_info, resolve_model
from .model.safety_models import (
prompt_guard_download_info,
prompt_guard_model_sku,
prompt_guard_download_info_map,
prompt_guard_model_sku_map,
)
prompt_guard = prompt_guard_model_sku()
prompt_guard_model_sku_map = prompt_guard_model_sku_map()
prompt_guard_download_info_map = prompt_guard_download_info_map()
for model_id in model_ids:
if model_id == prompt_guard.model_id:
model = prompt_guard
info = prompt_guard_download_info()
if model_id in prompt_guard_model_sku_map.keys():
model = prompt_guard_model_sku_map[model_id]
info = prompt_guard_download_info_map[model_id]
else:
model = resolve_model(model_id)
if model is None: