]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: c8297c6)
convert : add support of codeqwen due to tokenizer (#6707)
authorJunyang Lin <redacted>
Wed, 24 Apr 2024 07:16:21 +0000 (15:16 +0800)
committerGitHub <redacted>
Wed, 24 Apr 2024 07:16:21 +0000 (10:16 +0300)
commit3fec68be4e9577fc53158366d3b3af039c17bb1f
tree72db2fe074c20955d1c5e28fc8a87dcce0ef30aftree
parentc8297c6af5693555652c40b95974b95d49d2674dcommit | diff
convert : add support of codeqwen due to tokenizer (#6707)

* add support of codeqwen due to tokenizer

* override load_hparams

* fix typo

* fix load_params

* convert : fix whitespace

---------

Co-authored-by: Georgi Gerganov <redacted>
convert-hf-to-gguf.py diff | blob | history
Packaging of ggml-org/llama.cpp