Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fixes #249 #255

Merged
merged 1 commit into from
Jun 8, 2023
Merged

Fixes #249 #255

merged 1 commit into from
Jun 8, 2023

Conversation

pseudotensor
Copy link
Collaborator

@pseudotensor pseudotensor commented Jun 8, 2023

Fixes #249

image

with verbose=True in preprocess in h2oai_pipeline.py. Works whether have massive context:

reducing 28144 tokens, assuming average of 3 chars/token for 6144 characters
reducing 2064 tokens, assuming average of 2 chars/token for 4096 characters
using 1395 tokens with 4096 chars
Token indices sequence length is longer than the specified maximum sequence length for this model (28144 > 2048). 

Or largest max_new_tokens=2048:

reducing 28144 tokens, assuming average of 3 chars/token for 6144 characters
reducing 2064 tokens, assuming average of 2 chars/token for 4096 characters
using 1395 tokens with 4096 chars
Reduced max_new_tokens from 2048 -> 633

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
1 participant