multi-GPU support for mine_hard_negatives #2967
Open
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
UKPLab#2957) Required to avoid issues with loading expecting local files, but the root is kept on the Hub to avoid downloading the entire repository (with multiple model files, etc.)
Added support for multi-GPU encoding in sentence embeddings with model.encode_multi_process
…#2951) * Added the possibility of masking the prompts if the tokenizer is left-padded. * Simplify code * Remove unrelated changes * Move prompt_mask into the Transformer model * Added query and corpus prompts to Information Retrieval Evaluator * Fix for failing test * Fix for pooling when mask is not passed * Fix device placement for prompt_mask * Revert left-padding changes * Revert left-padding changes
…tiple evaluators (UKPLab#2963) Also rename "loss" to Validation Loss
* Add negatives in CachedGISTEmbedLoss * Add multi-negative n-tuples as valid inputs in 3 losses --------- Co-authored-by: Tom Aarsen <[email protected]>
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Outdated suggestions cannot be applied.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.
Added support for multi-GPU encoding in sentence embeddings with model.encode_multi_process