Updated make-ggml.py compatibility with more models and GGUF #3290
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
richardr1126
changed the title
ggerganov
approved these changes
Sep 27, 2023
joelkuiper
added a commit
to vortext/llama.cpp
that referenced
this pull request
Sep 27, 2023
…example * 'master' of github.com:ggerganov/llama.cpp: convert : remove bug in convert.py permute function (ggerganov#3364) make-ggml.py : compatibility with more models and GGUF (ggerganov#3290) gguf : fix a few general keys (ggerganov#3341) metal : reusing llama.cpp logging (ggerganov#3152) build : add ACCELERATE_NEW_LAPACK to fix warning on macOS Sonoma (ggerganov#3342) readme : add some recent perplexity and bpw measurements to READMES, link for k-quants (ggerganov#3340) cmake : fix build-info.h on MSVC (ggerganov#3309) docs: Fix typo CLBlast_DIR var. (ggerganov#3330) nix : add cuda, use a symlinked toolkit for cmake (ggerganov#3202)
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Outdated suggestions cannot be applied.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.
I have updated the script to work with all the model types HF --> GGUF conversions.
There is a new flag
--model_typetakes as input (llama, starcoder, falcon, baichuan, or gptneox). I have not tested with all models but can confirm llama and starcoder quanitize correctly with k-quants, and the falcon model only works with the legacy quants.