nemo_automodel.components.models.lfm3.processing
nemo_automodel.components.models.lfm3.processing
LFM3-VL processor assembled from the Qwen image and video processors of the pinned Transformers release.
Module Contents
Classes
API
Bases: Qwen3VLProcessor
Qwen3-VL prompt construction over LFM3-VL’s tokenizer and patch settings.
Released checkpoints name image and video processors that exist only as
remote code. Transformers 5.23 maps LFM3-VL to its Qwen2-VL image and
Qwen3-VL video processors instead; from_pretrained builds those from the
checkpoint’s stored settings, so no remote code runs.
Names of the tensors the processor returns, without Qwen3-VL’s multimodal token-type ids.
Load the tokenizer, chat template and patch settings of an LFM3-VL checkpoint.
Parameters:
Hub repository id or local checkpoint directory.
Hub loading options such as revision, cache_dir and token.
Returns: Lfm3VlProcessor
Processor backed by the native Qwen image and video processors.
Bases: ProcessingKwargs
Call-time defaults: LFM3-VL takes no multimodal token-type ids.