mirror/OpenLLM
1
0
Fork 0
mirror of https://github.com/bentoml/OpenLLM.git synced 2026-03-12 20:17:23 -04:00
Code Issues Packages Projects Releases Wiki Activity

refactor(cli): cleanup API (#592)

Browse Source 
* chore: remove unused imports

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* refactor(cli): update to only need model_id

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* feat: `openllm start model-id`

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* chore: add changelog

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* chore: update changelog notice

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* chore: update correct config and running tools

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* chore: update backward compat options and treat JSON outputs
corespondingly

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

---------

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
This commit is contained in:
Aaron Pham
2023-11-09 11:40:17 -05:00
committed by GitHub
parent 86f7acafa9
commit b8a2e8cf91
48 changed files with 1096 additions and 1047 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
openllm-python/src/openllm/serialisation/transformers/weights.py
View File

@@ -1,18 +1,40 @@
from __future__ import annotations
import traceback
import typing as t
import attr
from huggingface_hub import HfApi
from openllm_core.exceptions import Error
if t.TYPE_CHECKING:
from huggingface_hub.hf_api import ModelInfo as HfModelInfo
import openllm
from openllm_core._typing_compat import M
from openllm_core._typing_compat import T
__global_inst__ = None
__cached_id__: dict[str, HfModelInfo] = dict()
def Client() -> HfApi:
global __global_inst__ # noqa: PLW0603
if __global_inst__ is None: __global_inst__ = HfApi()
return __global_inst__
def ModelInfo(model_id: str, revision: str | None = None) -> HfModelInfo:
if model_id in __cached_id__: return __cached_id__[model_id]
try:
__cached_id__[model_id] = Client().model_info(model_id, revision=revision)
return __cached_id__[model_id]
except Exception as err:
traceback.print_exc()
raise Error(f'Failed to fetch {model_id} from huggingface.co') from err
def has_safetensors_weights(model_id: str, revision: str | None = None) -> bool:
return any(s.rfilename.endswith('.safetensors') for s in HfApi().model_info(model_id, revision=revision).siblings)
return any(s.rfilename.endswith('.safetensors') for s in ModelInfo(model_id, revision=revision).siblings)
@attr.define(slots=True)
class HfIgnore: