tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-23 03:08:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

mtmd : add **vision** support for Mistral Small 3.1 (#13231)

Browse Source 
* convert ok

* load ok, missing patch merger

* ah sheet it works

* update llava/readme

* add test

* fix test
This commit is contained in:
Xuan-Son Nguyen
2025-05-01 17:05:42 +02:00
committed by GitHub
parent 13c9a3319b
commit 8936784f7a
9 changed files with 112 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/llava/README.md
View File

@ -34,6 +34,9 @@ llama-mtmd-cli -hf ggml-org/SmolVLM2-500M-Video-Instruct-GGUF
# Pixtral 12B
llama-mtmd-cli -hf ggml-org/pixtral-12b-GGUF
# Mistral Small 3.1 24B (IQ2_M quantization)
llama-mtmd-cli -hf ggml-org/Mistral-Small-3.1-24B-Instruct-2503-GGUF --chat-template mistral-v7
```
## How it works and what is `mmproj`?
@ -73,3 +76,4 @@ For the following models, you can use `convert_hf_to_gguf.py`with `--mmproj` fla
- SmolVLM (from [HuggingFaceTB](https://huggingface.co/HuggingFaceTB))
- SmolVLM2 (from [HuggingFaceTB](https://huggingface.co/HuggingFaceTB))
- [Pixtral 12B](https://huggingface.co/mistral-community/pixtral-12b) - only works with `transformers`-compatible checkpoint
- [Mistral Small 3.1 24B](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503)