Use llama-8b-instruct tokenizer.json and tokenizer_config.json for llama3_8b_fp16 dataset
#953
+1
−1
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
…lama3_8b_fp16` dataset
renxida
approved these changes
Feb 11, 2025
monorimet
pushed a commit
that referenced
this pull request
Feb 13, 2025
…lama3_8b_fp16` dataset (#953) The tokenizers specified for this dataset are for `llama3_8b_fp16`, while the model is `llama3_8b_fp16_instruct`. The `eos_token` for `8b` and `8b-instruct` are different: ```text 8b: <|begin_of_text|> {generated_text} <|end_of_text|> <|end_of_text|> - 128001 8b-Instruct: <|begin_of_text|> {generated_text} <|eot_id|> <|eot_id|> - 128009 ``` Using the wrong config causes Llama to output text forever. Our model generated `128009`s, but the server doesn't recognize it as the proper stop token and keeps calling for generations. More details [here](#934 (comment))
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Outdated suggestions cannot be applied.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.
The tokenizers specified for this dataset are for
llama3_8b_fp16, while the model isllama3_8b_fp16_instruct. Theeos_tokenfor8band8b-instructare different:Using the wrong config causes Llama to output text forever. Our model generated
128009s, but the server doesn't recognize it as the proper stop token and keeps calling for generations.More details here