nemo_automodel.components.models.kimi_k3.multimodal

Native top-level Kimi K3 vision-language model.

Module Contents

Classes

Name	Description
`KimiK3ForConditionalGeneration`	Kimi K3 MoonViT3d tower, projector, and native KDA/MLA language model.

Functions

Name	Description
`_projector_config`	-
`_vision_tower_config`	-

Data

ModelClass

API

class nemo_automodel.components.models.kimi_k3.multimodal.KimiK3ForConditionalGeneration(
    config: nemo_automodel.components.models.kimi_k3.config.KimiK3Config,
    moe_config: nemo_automodel.components.moe.config.MoEConfig | None = None,
    backend: nemo_automodel.components.models.common.BackendConfig | None = None,
    kwargs: typing.Any = {}
)

Bases: KimiK3ForCausalLM

Kimi K3 MoonViT3d tower, projector, and native KDA/MLA language model.

ModelCapabilities

= KimiK3ForCausalLM.ModelCapabilities

mm_projector

= projector_cls(projector_config)

state_dict_adapter

vision_tower

nemo_automodel.components.models.kimi_k3.multimodal.KimiK3ForConditionalGeneration._extract_image_features(
    pixel_values: torch.Tensor,
    grid_thws: torch.Tensor
) -> list[torch.Tensor]

Encode packed pixel_values using grid_thws image/video geometry.

nemo_automodel.components.models.kimi_k3.multimodal.KimiK3ForConditionalGeneration._merge_input_ids_with_image_features(
    image_features: list[torch.Tensor],
    inputs_embeds: torch.Tensor,
    input_ids: torch.Tensor,
    attention_mask: torch.Tensor,
    labels: torch.Tensor | None = None
) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor | None, torch.Tensor]

Expand image placeholders in [batch, sequence] text tensors.

nemo_automodel.components.models.kimi_k3.multimodal.KimiK3ForConditionalGeneration.forward(
    input_ids: torch.Tensor | None = None,
    block_residual: torch.Tensor | None = None,
    pixel_values: torch.Tensor | None = None,
    grid_thws: torch.Tensor | None = None,
    attention_mask: torch.Tensor | None = None,
    position_ids: torch.Tensor | None = None,
    inputs_embeds: torch.Tensor | None = None,
    labels: torch.Tensor | None = None,
    logits_to_keep: int | torch.Tensor = 0,
    output_hidden_states: bool | None = None,
    kwargs: typing.Any = {}
) -> transformers.modeling_outputs.CausalLMOutputWithPast | torch.Tensor | tuple[torch.Tensor, torch.Tensor]

Run text-only or multimodal K3 inputs.

nemo_automodel.components.models.kimi_k3.multimodal.KimiK3ForConditionalGeneration.from_config(
    config: nemo_automodel.components.models.kimi_k3.config.KimiK3Config,
    moe_config: nemo_automodel.components.moe.config.MoEConfig | None = None,
    backend: nemo_automodel.components.models.common.BackendConfig | None = None,
    kwargs: typing.Any = {}
) -> 'KimiK3ForConditionalGeneration'

classmethod

nemo_automodel.components.models.kimi_k3.multimodal.KimiK3ForConditionalGeneration.from_pretrained(
    pretrained_model_name_or_path: str,
    model_args: typing.Any = (),
    kwargs: typing.Any = {}
) -> 'KimiK3ForConditionalGeneration'

classmethod

nemo_automodel.components.models.kimi_k3.multimodal._projector_config(
    config: nemo_automodel.components.models.kimi_k3.config.KimiK3Config
) -> types.SimpleNamespace

nemo_automodel.components.models.kimi_k3.multimodal._vision_tower_config(
    config: nemo_automodel.components.models.kimi_k3.config.KimiK3Config
)

nemo_automodel.components.models.kimi_k3.multimodal.ModelClass = KimiK3ForConditionalGeneration