Fix color getting reset before prompt output done #65
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
(cherry picked from commit 7eb2987)
44670
pushed a commit
to 44670/llama.cpp
that referenced
this pull request
Aug 2, 2023
* Long-range falcon upgrade (16k context) Default context is not 2048 The embedding rotation has been adapted to react to context and expected generation Uses "NTK" fourier aware scaling of the rotation space. 7B and 40B have been tested to work well up to a context of 8k Tests at > 8k are incoming once performance at these sizes works better RAM requirements for K/V caches: Falcon 7B at 8k context : ~2 GB RAM Falcon 40B at 8k context : ~5.5 GB RAM In addition falcon_eval() now uses a configuration struct instead of passing many parameters through multiple abstraction layers. This makes it much easier to pass new features from main into libfalcon * perplexity bugfix --------- Co-authored-by: John <cmt-nct@users.noreply.github.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This should fix the issue where sometimes the last few tokens of the initial prompt will not get colored correctly, because the color reset ANSI code was emitted early.