Skip to navigation

LFM3-VL-2B pairs the LFM3 language model with a vision encoder of gated 2D convolutions and bidirectional attention. It reads images and videos at their native resolution. The Hugging Face configuration declares the Lfm3VlForConditionalGeneration architecture.

Fine-Tune LFM3-VL-2B

Follow the installation instructions, then run the recipe from the repository root:

automodel examples/vlm_finetune/lfm3/lfm3_vl_2b_medpix.yaml --nproc-per-node 8

Choose a Workflow

GoalStart Here
Supervised fine-tuning (SFT) on MedPixUse lfm3_vl_2b_medpix.yaml. Dataset: MedPix-VQA.

The checkpoint’s processor configuration names image and video processors that exist only as remote code. NeMo AutoModel builds the equivalent Qwen2-VL image and Qwen3-VL video processors from the stored settings, the same mapping Transformers 5.23.0 uses, so AutoProcessor.from_pretrained works without trust_remote_code. The language model applies the rotary-embedding handling described for LFM3-1.7B.

Model Reference

Model Architecture

PropertyValue
TaskImage-Text-to-Text
ArchitectureLfm3VlForConditionalGeneration
Parameters2B
Hugging Face OrganizationLiquidAI

Available Models

ModelHF ID
LFM3-VL 2BLiquidAI/LFM3-VL-2B