Add support for bigscience/bloomz #25
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
mayank31398
force-pushed
the
mayank/bloomz
branch
from
23f4ff7
to
989b92c
Compare
mayank31398
force-pushed
the
mayank/bloomz
branch
4 times, most recently
from
f084033
to
448d3f8
Compare
mayank31398
force-pushed
the
mayank/bloomz
branch
from
448d3f8
to
773e830
Compare
mayank31398
force-pushed
the
mayank/bloomz
branch
from
ce5ebf3
to
8938221
Compare
njhill
reviewed
Nov 7, 2022
njhill
reviewed
Nov 7, 2022
| elif model_name == DS_INFERENCE_BLOOM_INT8: | ||
| return "int8" | ||
|
|
||
|
|
||
| def get_torch_dtype(dtype_str: str) -> torch.dtype: | ||
| if dtype_str == "bf16": |
There was a problem hiding this comment.
nit: The type hints in the get_str_dtype func below are the wrong way around. It should take a torch.dtype and return a str
inference_server/models/utils.py
Outdated
Comment on lines
4
to
6
| from .ds_inference import DSInferenceModel | ||
| from .ds_zero import DSZeROModel | ||
| from .hf_accelerate import HFAccelerateModel |
There was a problem hiding this comment.
Could be good to conditionally import these to avoid depending on non-required libraries when only one of them is used
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.