Minor Changes on Top of Isamus EXL2 PR (Docs, Enable FSM/CFG, Fix Tokenizer) #1191
Conversation
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
lapp0
changed the title
Fix comment Fixed precommit issues Removed text Basic draft done Passed local test Fixed tests+precommit Revert change for pyairports Fixed precommit Wrap up Remove | for union Attempt changing to List Fixed for 3.8 Adding exllamav2 to optional dependency Fixed model Changed to fork Fix format Changed order Skip exllamav2 tests Attempt fixing coverage Attempt fix coverage Remove flash-attn requirement Fixed fixture tests Removed lora Passed coverage Added back transformers install Fixed per review Made coverage 100%
fix exl bug: sometimes piece_to_id not populated, but get_piece_to_id() still works fix exl bug: sometimes piece_to_id not populated, but get_piece_to_id() still works enable exl2 in generate.cfg cleate OutlinesExLlamaV2Tokenizer rather than monkey patching
lapp0
force-pushed
the
exllamav2_filter
branch
from
4770023 to
a59c26f
Compare
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Outdated suggestions cannot be applied.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.
@isamu-isozaki did a great job implementing a fully functioning
outlines.models.exllamav2. This PR introduces minor fixes and a documentation update.This PR rebases with main and squashes his commits into one: d1f5609
Changes
New
models.exllamav2enablegenerate.cfgandgenerate.fsmCloses
exllamav2integration #807