Right now this is a draft in order to discuss and experiment with. We still need to add Baichuan 1, and there is currently an issue with compatibility for Baichuan itself for at least one of the models we want to support. A lot of the configuration has been complete. We need to add a config variable for the use_fast variable for the tokenizer. Right now it is set to false for a single architecture, but it varies from model to model on Baichuan.
Beyond that, there are issues that seem related to #569 and #570 with this model. This model supports both Mandarin and English. At the moment generations are mixing the two languages together, which seems to be an issue with implementation accuracy.
Fixes #622
Type of change
Please delete options that are not relevant.
[ ] Bug fix (non-breaking change which fixes an issue)
[x] New feature (non-breaking change which adds functionality)
[ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
[x] This change requires a documentation update
Screenshots
Please attach before and after screenshots of the change if applicable.
Checklist:
[x] I have commented my code, particularly in hard-to-understand areas
[ ] I have made corresponding changes to the documentation
[ ] My changes generate no new warnings
[ ] I have added tests that prove my fix is effective or that my feature works
[x] New and existing unit tests pass locally with my changes
[c] I have not rewritten tests relating to key interfaces which would affect backward compatibility
Description
Right now this is a draft in order to discuss and experiment with. We still need to add Baichuan 1, and there is currently an issue with compatibility for Baichuan itself for at least one of the models we want to support. A lot of the configuration has been complete. We need to add a config variable for the
use_fast
variable for the tokenizer. Right now it is set to false for a single architecture, but it varies from model to model on Baichuan.Beyond that, there are issues that seem related to #569 and #570 with this model. This model supports both Mandarin and English. At the moment generations are mixing the two languages together, which seems to be an issue with implementation accuracy.
Fixes #622
Type of change
Please delete options that are not relevant.
Screenshots
Please attach before and after screenshots of the change if applicable.
Checklist: