LLaVA

Currently this implementation supports llava-v1.5 variants, as well as llava-1.6 llava-v1.6 variants.

The pre-converted 7b and 13b models are available. For llava-1.6 a variety of prepared gguf models are available as well 7b-34b

After API is confirmed, more models will be supported / uploaded.

Usage

Build the llama-mtmd-cli binary.

After building, run: ./llama-mtmd-cli to see the usage. For example:

./llama-mtmd-cli -m ../llava-v1.5-7b/ggml-model-f16.gguf \
    --mmproj ../llava-v1.5-7b/mmproj-model-f16.gguf \
    --chat-template vicuna

note: A lower temperature like 0.1 is recommended for better quality. add --temp 0.1 to the command to do so. note: For GPU offloading ensure to use the -ngl flag just like usual

LLaVA 1.5

Clone a LLaVA and a CLIP model (available options). For example:

git clone https://huggingface.co/liuhaotian/llava-v1.5-7b

git clone https://huggingface.co/openai/clip-vit-large-patch14-336

Install the required Python packages:

pip install -r tools/mtmd/requirements.txt

Use llava_surgery.py to split the LLaVA model to LLaMA and multimodel projector constituents:

python ./tools/mtmd/llava_surgery.py -m ../llava-v1.5-7b

Use convert_image_encoder_to_gguf.py to convert the LLaVA image encoder to GGUF:

python ./tools/mtmd/convert_image_encoder_to_gguf.py -m ../clip-vit-large-patch14-336 --llava-projector ../llava-v1.5-7b/llava.projector --output-dir ../llava-v1.5-7b

Use examples/convert_legacy_llama.py to convert the LLaMA part of LLaVA to GGUF:

python ./examples/convert_legacy_llama.py ../llava-v1.5-7b --skip-unknown

Now both the LLaMA part and the image encoder are in the llava-v1.5-7b directory.

LLaVA 1.6 gguf conversion

First clone a LLaVA 1.6 model:

git clone https://huggingface.co/liuhaotian/llava-v1.6-vicuna-7b

Install the required Python packages:

pip install -r tools/mtmd/requirements.txt

Use llava_surgery_v2.py which also supports llava-1.5 variants pytorch as well as safetensor models:

python tools/mtmd/llava_surgery_v2.py -C -m ../llava-v1.6-vicuna-7b/

you will find a llava.projector and a llava.clip file in your model directory

Copy the llava.clip file into a subdirectory (like vit), rename it to pytorch_model.bin and add a fitting vit configuration to the directory:

mkdir vit
cp ../llava-v1.6-vicuna-7b/llava.clip vit/pytorch_model.bin
cp ../llava-v1.6-vicuna-7b/llava.projector vit/
curl -s -q https://huggingface.co/cmp-nct/llava-1.6-gguf/raw/main/config_vit.json -o vit/config.json

Create the visual gguf model:

python ./tools/mtmd/convert_image_encoder_to_gguf.py -m vit --llava-projector vit/llava.projector --output-dir vit --clip-model-is-vision

This is similar to llava-1.5, the difference is that we tell the encoder that we are working with the pure vision model part of CLIP

Then convert the model to gguf format:

python ./examples/convert_legacy_llama.py ../llava-v1.6-vicuna-7b/ --skip-unknown

And finally we can run the llava cli using the 1.6 model version:

./llama-mtmd-cli -m ../llava-v1.6-vicuna-7b/ggml-model-f16.gguf --mmproj vit/mmproj-model-f16.gguf

note llava-1.6 needs more context than llava-1.5, at least 3000 is needed (just run it at -c 4096)

note llava-1.6 greatly benefits from batched prompt processing (defaults work)

note if the language model in step 6) is incompatible with the legacy conversion script, the easiest way handle the LLM model conversion is to load the model in transformers, and export only the LLM from the llava next model.

import os
import transformers

model_path = ...
llm_export_path = ...

tokenizer = transformers.AutoTokenizer.from_pretrained(model_path)
model = transformers.AutoModelForImageTextToText.from_pretrained(model_path)

tokenizer.save_pretrained(llm_export_path)
model.language_model.save_pretrained(llm_export_path)

Then, you can convert the LLM using the convert_hf_to_gguf.py script, which handles more LLM architectures.

Chat template

For llava-1.5 and llava-1.6, you need to use vicuna chat template. Simply add --chat-template vicuna to activate this template.

How to know if you are running in llava-1.5 or llava-1.6 mode

When running llava-cli you will see a visual information right before the prompt is being processed:

Llava-1.5: encode_image_with_clip: image embedding created: 576 tokens

Llava-1.6 (anything above 576): encode_image_with_clip: image embedding created: 2880 tokens

Alternatively just pay notice to how many "tokens" have been used for your prompt, it will also show 1000+ tokens for llava-1.6