]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
mtmd : Support Pixtral 12B (#13065)
authorXuan-Son Nguyen <redacted>
Wed, 23 Apr 2025 18:21:59 +0000 (20:21 +0200)
committerGitHub <redacted>
Wed, 23 Apr 2025 18:21:59 +0000 (20:21 +0200)
commitecda2ec4b347031a9b8a89ee2efc664ce63f599c
tree4692e3274b405d3bf9cf66c9e168a388c69217c3
parenteb1776b15a32d832f1266deeeab75b9d255c5849
mtmd : Support Pixtral 12B (#13065)

* add pixtral text model (vision is wip)

* cgraph ok, just missing 2D RoPE

* fix bad rebase

* first working version

* fix problem with img_break token

* support dynamic image size

* update docs

* update test script
14 files changed:
convert_hf_to_gguf.py
convert_hf_to_gguf_update.py
docs/multimodal/gemma3.md
examples/llava/README.md
examples/llava/clip-impl.h
examples/llava/clip.cpp
examples/llava/mtmd.cpp
examples/llava/tests.sh
gguf-py/gguf/constants.py
gguf-py/gguf/tensor_mapping.py
include/llama.h
models/ggml-vocab-pixtral.gguf.inp [new file with mode: 0644]
models/ggml-vocab-pixtral.gguf.out [new file with mode: 0644]
src/llama-vocab.cpp