Conversation
JulienVig
force-pushed
the
654-improve-gpt-julien
branch
20 times, most recently
from
1d88d35 to
03e5c7d
Compare
tharvik
requested changes
Nov 1, 2024
Collaborator
tharvik
left a comment
tharvik
left a comment
There was a problem hiding this comment.
superb work, thanks for clearing the GPT's mud, every comments makes it more understandable!
yeah, sadly, as I forgot to merge the processing PR (#781) before you branched off, the whole processing pipeline changed a lot. sorry for the toes stepping (hopefully, it will simplify this PR).
btw, it seems that @xenova/transformer has been recently updated to @huggingface/transformer. did you try it out? maybe it'll help with the tokenizer usage (doesn't look much changed to me but you know best)
JulienVig
force-pushed
the
654-improve-gpt-julien
branch
from
0a28b81 to
f7f96dc
Compare
Member
|
maybe rename block size to context len, that would be more specific |
JulienVig
force-pushed
the
654-improve-gpt-julien
branch
3 times, most recently
from
68d957b to
8cbc96e
Compare
Merged
tharvik
approved these changes
Dec 2, 2024
Collaborator
tharvik
left a comment
tharvik
left a comment
There was a problem hiding this comment.
only cosmetic comments, thanks for the huge amount of work 🎉
JulienVig
force-pushed
the
654-improve-gpt-julien
branch
from
8cbc96e to
0781b7c
Compare
Collaborator
Author
…odeling head and attention bias
… implement topk sampling
…ers following GPT2 convention, use LogLayer
… and language modeling head
…red task parameter for text tasks
…he model init config
JulienVig
force-pushed
the
654-improve-gpt-julien
branch
from
0781b7c to
30de4fb
Compare
Member
|
well done! |
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Closes #654