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

fix prompt guard (#177)

Browse source 
Several other fixes to configure. Add support for 1b/3b models in ollama.
This commit is contained in:
Ashwin Bharambe 2024-10-03 11:07:53 -07:00 • committed by GitHub
parent b9b1e8b08b
commit 210b71b0ba
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 50 additions and 45 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -7,6 +7,10 @@
from llama_stack.distribution.datatypes import RemoteProviderConfig
class OllamaImplConfig(RemoteProviderConfig):
port: int = 11434
async def get_adapter_impl(config: RemoteProviderConfig, _deps):
from .ollama import OllamaInferenceAdapter

3
llama_stack/providers/adapters/inference/ollama/ollama.py
View file

@ -23,9 +23,10 @@ from llama_stack.providers.utils.inference.routable import RoutableProviderForMo
# TODO: Eventually this will move to the llama cli model list command
# mapping of Model SKUs to ollama models
OLLAMA_SUPPORTED_SKUS = {
# "Llama3.1-8B-Instruct": "llama3.1",
"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",
"Llama3.2-3B-Instruct": "llama3.2:3b-instruct-fp16",
}