LLaVA#
LLaVA (Large Language and Vision Assistant) is a pioneering open-source multimodal model connecting a vision encoder to a language model via a projection layer. Multiple versions and variants are supported via the llava-hf organization on Hugging Face.
Task |
Image-Text-to-Text |
Architecture |
|
Parameters |
7B – 34B |
HF Org |
Available Models#
LLaVA-1.5 (
LlavaForConditionalGeneration): 7B, 13BLLaVA-1.6 / LLaVA-NeXT (
LlavaNextForConditionalGeneration): 7B, 34BLLaVA-NeXT-Video (
LlavaNextVideoForConditionalGeneration): 7BLLaVA-OneVision (
LlavaOnevisionForConditionalGeneration): 7B
Architectures#
LlavaForConditionalGeneration— LLaVA 1.5LlavaNextForConditionalGeneration— LLaVA-NeXT / 1.6LlavaNextVideoForConditionalGeneration— LLaVA-NeXT-VideoLlavaOnevisionForConditionalGeneration— LLaVA-OneVision
Example HF Models#
Model |
HF ID |
|---|---|
LLaVA 1.5 7B |
|
LLaVA 1.5 13B |
|
LLaVA-NeXT Mistral 7B |
|
LLaVA-NeXT 34B |
|
LLaVA-NeXT-Video 7B |
|
LLaVA-OneVision 7B |
Try with NeMo AutoModel#
Install NeMo AutoModel and follow the fine-tuning guide to configure a recipe for this model.
1. Install (full instructions):
pip install nemo-automodel
2. Clone the repo to get example recipes you can adapt:
git clone https://github.com/NVIDIA-NeMo/Automodel.git
cd Automodel
3. Fine-tune by adapting a base VLM recipe — override the model ID on the CLI:
automodel --nproc-per-node=8 examples/vlm_finetune/gemma3/gemma3_vl_4b_cord_v2.yaml \
--model.pretrained_model_name_or_path <MODEL_HF_ID>
Replace <MODEL_HF_ID> with the model ID from Example HF Models above.
Run with Docker
1. Pull the container and mount a checkpoint directory:
docker run --gpus all -it --rm \
--shm-size=8g \
-v $(pwd)/checkpoints:/opt/Automodel/checkpoints \
nvcr.io/nvidia/nemo-automodel:26.02.00
2. The recipes are at /opt/Automodel/examples/ — navigate there:
cd /opt/Automodel
3. Fine-tune:
automodel --nproc-per-node=8 examples/vlm_finetune/gemma3/gemma3_vl_4b_cord_v2.yaml \
--model.pretrained_model_name_or_path <MODEL_HF_ID>
See the Installation Guide and VLM Fine-Tuning Guide.
Fine-Tuning#
See the VLM Fine-Tuning Guide.