From 27b3a2c9fc3fd85e8c52ac0ed9c5a2aefe395f97 Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Wed, 1 May 2024 18:21:17 +0200 Subject: [PATCH] Fix: "Fixing" double BOS for mistral too. (#1843) # What does this PR do? Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. --- server/text_generation_server/models/flash_mistral.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/server/text_generation_server/models/flash_mistral.py b/server/text_generation_server/models/flash_mistral.py index 6959e2ec..85e93543 100644 --- a/server/text_generation_server/models/flash_mistral.py +++ b/server/text_generation_server/models/flash_mistral.py @@ -121,6 +121,11 @@ class FlashMistralBatch(FlashCausalLMBatch): requests_idx_mapping[r.id] = i tokenized_input = tokenized_input[-r.truncate :] + if ( + tokenized_input[0] == tokenizer.bos_token_id + and tokenized_input[1] == tokenizer.bos_token_id + ): + tokenized_input = tokenized_input[1:] input_length = len(tokenized_input) input_lengths.append(input_length)