Merge pull request #75 from DocShotgun/main

Additional clarification for override_base_seq_len
This commit is contained in:
Brian Dashore
2024-03-03 01:30:45 -05:00
committed by GitHub

View File

@@ -73,7 +73,8 @@ model:
# Overrides base model context length (default: Empty)
# WARNING: Don't set this unless you know what you're doing!
# Only use this if the model's base sequence length in config.json is incorrect (ex. Mistral/Mixtral models)
# Again, do NOT use this for configuring context length, use max_seq_len above ^
# Only use this if the model's base sequence length in config.json is incorrect (ex. Mistral 7B)
#override_base_seq_len:
# Automatically allocate resources to GPUs (default: True)