enable falcon-180b inference#697
Closed
schoi-habana wants to merge 8 commits into
Closed
Conversation
schoi-habana
requested review from
bhargaveede,
regisss,
ssarkar2 and
vivekgoe
as code owners
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
schoi-habana
force-pushed
the
dev/schoi/falcon_180b_loading_ckpt
branch
from
6659dca to
fbf1bd2
Compare
Collaborator
|
@schoi-habana From what I understood in this PR, loading safetensors checkpoint with DeepSpeed is not supported yet with Habana's DeepSpeed fork v1.14. So my understanding is that it will work when v1.15 is released right? |
Collaborator
Author
|
@regisss that's true. Please merge this after 1.15.0 release |
schoi-habana
force-pushed
the
dev/schoi/falcon_180b_loading_ckpt
branch
from
a24421c to
e40e9cc
Compare
Collaborator
Author
|
no longer needed as #773 is a permanent solution |
gplutop7
pushed a commit
to HabanaAI/optimum-habana-fork
that referenced
this pull request
Oct 15, 2025
…e#2262) (huggingface#697) Co-authored-by: Iman Gohari <s.m.iman.gohari@intel.com>
gplutop7
pushed a commit
to HabanaAI/optimum-habana-fork
that referenced
this pull request
Nov 6, 2025
…e#2262) (huggingface#697) Co-authored-by: Iman Gohari <s.m.iman.gohari@intel.com>
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
1 The current code can load only .bin or .pt whereas Falcon-180B ckpt files are in .safetensors format. This change enabled loading ckpt files in .safetensor format
2 The ValueError "The following model_kwargs are not used by the model: ['token_type_ids'] )" is addressed by introducing a workaround that removes ‘token_type_ids’ from the model_kwargs.
Before submitting