]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: f3e2b4f)
llama : add MiniCPM support (#5346)
authorrunfuture <redacted>
Wed, 7 Feb 2024 06:15:56 +0000 (14:15 +0800)
committerGitHub <redacted>
Wed, 7 Feb 2024 06:15:56 +0000 (08:15 +0200)
commit316c7faf7740fa98ea68f1445f4505810f706b9e
tree3e92df4e54d13e4dddb94b627792dcdedb62118dtree
parentf3e2b4fa3f81a410ecb7dec929c259ef8d8dbb7dcommit | diff
llama : add MiniCPM support (#5346)

* support minicpm arch.

* fix tab/space typo.

* convert minicpm model via convert-hf-gguf.py

* try to make tokenizer work

* fix bug for quantize minicpm

* fix for flake8 lint

* remove convert-minicpm.py

* fix for editorconfig

* correct minicpm model type (size)

* constants expanded for minicpm

* Minor change of the constant names for minicpm
convert-hf-to-gguf.py diff | blob | history
gguf-py/gguf/constants.py diff | blob | history
llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp