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.

Sign up for GitHub

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

fix: token suspicion adjustment #477

Merged
merged 2 commits into from
Jan 21, 2025
Merged

fix: token suspicion adjustment #477

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7f898a1
fix: token suspicion adjustment
tazlin Jan 17, 2025
f6a7915
fix: add two gradations to the text token/s thresholds
tazlin Jan 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 16 additions & 5 deletions horde/classes/kobold/processing_generation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,13 +111,24 @@ def record(self, things_per_sec, kudos):
return
param_multiplier = model_reference.get_text_model_multiplier(self.model)
unreasonable_speed = hv.suspicion_thresholds["text"]

# max_speed_per_multiplier = {
# 70: 12,
# 40: 22,
# 20: 35,
# 13: 50,
# 7: 70,
# }

# Once upon a time, before batching and other optimizations, these were the speeds we considered unreasonable
# but new paradigms, backends and breakthroughs have made these numbers increasingly inaccurate or irrelevant.

max_speed_per_multiplier = {
70: 12,
40: 22,
20: 35,
13: 50,
7: 70,
70: 30,
14: 100,
8: 150,
tazlin marked this conversation as resolved.
Show resolved Hide resolved
}

for params_count in max_speed_per_multiplier:
if param_multiplier >= params_count:
unreasonable_speed = max_speed_per_multiplier[params_count]
Expand Down
Loading