Add support of Falcon models (7b, 40b, 180b) to DeepSpeed-FastGen #4790
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Outdated suggestions cannot be applied.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.
This PR adds support for Falcon models 7b, 40b and 180b. Note that 40b and 180b models have a different model architecture than the 7b variant.
Falcon-7B:
Huggingface output with prompt "DeepSpeed is":
DeepSpeed-FastGen output with prompt "DeepSpeed is" with 2-way sharding:
Falcon-40B:
Huggingface output with prompt "DeepSpeed is":
DeepSpeed-FastGen output with prompt "DeepSpeed is" with 2-way sharding:
Falcon-180B:
Huggingface output with prompt "DeepSpeed is":
DeepSpeed-FastGen output with prompt "DeepSpeed is" with 8-way sharding: