For Mistral 7B - Generate Text using Input Embeddings + Add no_repeat_ngram_size Support #86
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
davidshtian
changed the title
# for free
to join this conversation on GitHub.
Already have an account?
# 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Outdated suggestions cannot be applied.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.
Description of changes:
Currently, the Mistral 7B model does not take input_embeds (skip the embedding layer) as accepted input, but only input_ids. While lots of multimodal models are using Mistral as base LLM, and will send the input_embeds directly to LLM, it would be great and general to support this feature. And also add no_repeat_ngram_size sampling parameter support. Hope it helps~ Thanks~
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.