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

Support for Llama3.2 models and Swift SDK (#98)

Browse source
This commit is contained in:
Ashwin Bharambe 2024-09-25 10:29:58 -07:00 • committed by GitHub
parent 95abbf576b
commit 56aed59eb4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
56 changed files with 3745 additions and 630 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/adapters/inference/tgi/tgi.py
View file

@ -14,7 +14,9 @@ from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.datatypes import StopReason
from llama_models.llama3.api.tokenizer import Tokenizer
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.providers.utils.inference.prepare_messages import prepare_messages
from llama_stack.providers.utils.inference.augment_messages import (
augment_messages_for_tools,
)
from .config import TGIImplConfig
@ -95,7 +97,7 @@ class TGIAdapter(Inference):
logprobs=logprobs,
)
messages = prepare_messages(request)
messages = augment_messages_for_tools(request)
model_input = self.formatter.encode_dialog_prompt(messages)
prompt = self.tokenizer.decode(model_input.tokens)