Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-20 01:31:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

merged pixtral support, not fully working

Browse Source
This commit is contained in:
Concedo
2025-04-24 15:27:02 +08:00
parent 8f1edcbdac 5630406959
commit 28a2723100
24 changed files with 1279 additions and 512 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/multimodal/gemma3.md
+6 -6
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
```