text-generation-inference
text-generation-inference copied to clipboard
max_total_tokens is hardcoded to 1512 and cant be changed from SageMaker.
System Info
max_total_tokens is hardcoded to 1512 and cant be changed from SageMaker.
Information
- [ ] Docker
- [ ] The CLI directly
Tasks
- [ ] An officially supported command
- [ ] My own modifications
Reproduction
If the token size exceeds 1512 it gives error.
Expected behavior
There should be a option to increase the same using env variable.