phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-08 19:10:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Introduce model_store, shield_store, memory_bank_store

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-06 16:29:33 -07:00 • committed by Ashwin Bharambe
parent e45a417543
commit 91e0063593
19 changed files with 172 additions and 297 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/adapters/inference/ollama/ollama.py
View file

@ -21,7 +21,7 @@ from llama_stack.providers.utils.inference.augment_messages import (
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
OLLAMA_SUPPORTED_SKUS = {
OLLAMA_SUPPORTED_MODELS = {
"Llama3.1-8B-Instruct": "llama3.1:8b-instruct-fp16",
"Llama3.1-70B-Instruct": "llama3.1:70b-instruct-fp16",
"Llama3.2-1B-Instruct": "llama3.2:1b-instruct-fp16",
@ -33,7 +33,7 @@ OLLAMA_SUPPORTED_SKUS = {
class OllamaInferenceAdapter(ModelRegistryHelper, Inference):
def __init__(self, url: str) -> None:
ModelRegistryHelper.__init__(
self, stack_to_provider_models_map=OLLAMA_SUPPORTED_SKUS
self, stack_to_provider_models_map=OLLAMA_SUPPORTED_MODELS
)
self.url = url
tokenizer = Tokenizer.get_instance()