git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

overview / pkg / ggml / sources / llama.cpp / commit

author	Xuan-Son Nguyen <redacted>
	Fri, 2 May 2025 15:17:15 +0000 (17:17 +0200)
committer	GitHub <redacted>
	Fri, 2 May 2025 15:17:15 +0000 (17:17 +0200)
commit	074e42ab31de4c99aa7d9d2d239660f64b2380d6
tree	de537a545567059f2b149fcb58c4741d375126bd	tree
parent	c642bc014c105728ce45015813351dc5a37f60a2	commit \| diff

convert : converting mmproj for Qwen2/2.5VL from convert_hf_to_gguf (#13209)

* wip

* qwen2.5vl ok

* vision: fix models missing "text_config"

* add test

* fix test repo name

* fix 32B model

* Revert "fix 32B model"

This reverts commit 651752f1ae25fe8a01c1e57c18cf2eca80b2774e.

* clarify about 32B

* rm qwen surgery script

* update llava/readme

* move V_ENC_EMBD_PATCH handling to Qwen2VLVisionModel

convert_hf_to_gguf.py		diff \| blob \| history
examples/llava/README.md		diff \| blob \| history
examples/llava/qwen2_vl_surgery.py	[deleted file]	blob \| history
examples/llava/tests.sh		diff \| blob \| history
gguf-py/gguf/constants.py		diff \| blob \| history
gguf-py/gguf/gguf_writer.py		diff \| blob \| history
gguf-py/gguf/tensor_mapping.py		diff \| blob \| history

Packaging of ggml-org/llama.cpp

RSS Atom