ros/LlamaFactory
1
0
Fork 0
mirror of https://github.com/hiyouga/LlamaFactory.git synced 2026-02-02 08:33:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

support mllm hf inference

Browse Source 
Former-commit-id: 2c7c01282acd7ddabbb17ce3246b8dae4bc4b8cf
This commit is contained in:
hiyouga
2024-04-26 05:34:58 +08:00
parent 10a6c395bb
commit 23b881bff1
23 changed files with 128 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
src/llmtuner/chat/chat_model.py
View File

@@ -8,6 +8,8 @@ from .vllm_engine import VllmEngine
if TYPE_CHECKING:
from numpy.typing import NDArray
from .base_engine import BaseEngine, Response
@@ -36,9 +38,10 @@ class ChatModel:
messages: Sequence[Dict[str, str]],
system: Optional[str] = None,
tools: Optional[str] = None,
image: Optional["NDArray"] = None,
**input_kwargs,
) -> List["Response"]:
task = asyncio.run_coroutine_threadsafe(self.achat(messages, system, tools, **input_kwargs), self._loop)
task = asyncio.run_coroutine_threadsafe(self.achat(messages, system, tools, image, **input_kwargs), self._loop)
return task.result()
async def achat(
@@ -46,18 +49,20 @@ class ChatModel:
messages: Sequence[Dict[str, str]],
system: Optional[str] = None,
tools: Optional[str] = None,
image: Optional["NDArray"] = None,
**input_kwargs,
) -> List["Response"]:
return await self.engine.chat(messages, system, tools, **input_kwargs)
return await self.engine.chat(messages, system, tools, image, **input_kwargs)
def stream_chat(
self,
messages: Sequence[Dict[str, str]],
system: Optional[str] = None,
tools: Optional[str] = None,
image: Optional["NDArray"] = None,
**input_kwargs,
) -> Generator[str, None, None]:
generator = self.astream_chat(messages, system, tools, **input_kwargs)
generator = self.astream_chat(messages, system, tools, image, **input_kwargs)
while True:
try:
task = asyncio.run_coroutine_threadsafe(generator.__anext__(), self._loop)
@@ -70,9 +75,10 @@ class ChatModel:
messages: Sequence[Dict[str, str]],
system: Optional[str] = None,
tools: Optional[str] = None,
image: Optional["NDArray"] = None,
**input_kwargs,
) -> AsyncGenerator[str, None]:
async for new_token in self.engine.stream_chat(messages, system, tools, **input_kwargs):
async for new_token in self.engine.stream_chat(messages, system, tools, image, **input_kwargs):
yield new_token
def get_scores(