Skip to content

Conversation

BarfingLemurs
Copy link
Contributor

@BarfingLemurs BarfingLemurs commented Sep 26, 2023

Some of the most useful data and charts for quantization comparisons is not so easily found for new users approaching this repository.

  • add a link to k-quants PRs in the main README
  • added current perplexity and bpw scores for only some models to respective example readmes

@ggerganov ggerganov merged commit ffe88a3 into ggml-org:master 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 (ggml-org#3364)
  make-ggml.py : compatibility with more models and GGUF (ggml-org#3290)
  gguf : fix a few general keys (ggml-org#3341)
  metal : reusing llama.cpp logging (ggml-org#3152)
  build : add ACCELERATE_NEW_LAPACK to fix warning on macOS Sonoma (ggml-org#3342)
  readme : add some recent perplexity and bpw measurements to READMES, link for k-quants (ggml-org#3340)
  cmake : fix build-info.h on MSVC (ggml-org#3309)
  docs: Fix typo CLBlast_DIR var. (ggml-org#3330)
  nix : add cuda, use a symlinked toolkit for cmake (ggml-org#3202)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants