tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

mtmd : Support Pixtral 12B (#13065)

Browse Source 
* 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
This commit is contained in:
Xuan-Son Nguyen
2025-04-23 20:21:59 +02:00
committed by GitHub
parent eb1776b15a
commit ecda2ec4b3
14 changed files with 643 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
docs/multimodal/gemma3.md
View File

@ -11,15 +11,15 @@ You can use pre-quantized model from [ggml-org](https://huggingface.co/ggml-org)
```bash
# build
cmake -B build
cmake --build build --target llama-gemma3-cli
cmake --build build --target llama-mtmd-cli
# alternatively, install from brew (MacOS)
brew install llama.cpp
# run it
llama-gemma3-cli -hf ggml-org/gemma-3-4b-it-GGUF
llama-gemma3-cli -hf ggml-org/gemma-3-12b-it-GGUF
llama-gemma3-cli -hf ggml-org/gemma-3-27b-it-GGUF
llama-mtmd-cli -hf ggml-org/gemma-3-4b-it-GGUF
llama-mtmd-cli -hf ggml-org/gemma-3-12b-it-GGUF
llama-mtmd-cli -hf ggml-org/gemma-3-27b-it-GGUF
# note: 1B model does not support vision
```
@ -44,8 +44,8 @@ What you need:
```bash
# build
cmake -B build
cmake --build build --target llama-gemma3-cli
cmake --build build --target llama-mtmd-cli
# run it
./build/bin/llama-gemma3-cli -m {text_model}.gguf --mmproj mmproj.gguf --image your_image.jpg
./build/bin/llama-mtmd-cli -m {text_model}.gguf --mmproj mmproj.gguf --image your_image.jpg
```