nemo_automodel.components.models.minimax_m2.model

Module Contents

Classes

Name	Description
`Block`	MiniMax-M2 transformer block with attention + MoE.
`MiniMaxM2ForCausalLM`	-
`MiniMaxM2Model`	-

Data

ModelClass

API

class nemo_automodel.components.models.minimax_m2.model.Block(
    layer_idx: int,
    config: typing.Any,
    moe_config: nemo_automodel.components.moe.layers.MoEConfig,
    backend: nemo_automodel.components.models.common.BackendConfig
)

Bases: Module

MiniMax-M2 transformer block with attention + MoE.

input_layernorm

mlp

= MoE(moe_config, backend)

post_attention_layernorm

self_attn

= MiniMaxM2Attention(config, backend)

nemo_automodel.components.models.minimax_m2.model.Block.forward(
    x: torch.Tensor,
    freqs_cis: torch.Tensor,
    attention_mask: torch.Tensor | None = None,
    padding_mask: torch.Tensor | None = None,
    attn_kwargs: typing.Any = {}
) -> torch.Tensor

nemo_automodel.components.models.minimax_m2.model.Block.init_weights(
    buffer_device: torch.device
)

class nemo_automodel.components.models.minimax_m2.model.MiniMaxM2ForCausalLM(
    config: typing.Any,
    moe_config: nemo_automodel.components.moe.layers.MoEConfig | None = None,
    backend: nemo_automodel.components.models.common.BackendConfig | None = None,
    kwargs = {}
)

Bases: HFCheckpointingMixin, Module, MoEFSDPSyncMixin

_keep_in_fp32_modules_strict

backend

= backend or BackendConfig()

lm_head

model

state_dict_adapter

tie_word_embeddings_support

TieSupport = TieSupport.UNTIED_ONLY

nemo_automodel.components.models.minimax_m2.model.MiniMaxM2ForCausalLM.forward(
    input_ids: torch.Tensor,
    position_ids: torch.Tensor | None = None,
    attention_mask: torch.Tensor | None = None,
    padding_mask: torch.Tensor | None = None,
    logits_to_keep: typing.Union[int, torch.Tensor] = 0,
    output_hidden_states: bool | None = None,
    attn_kwargs: typing.Any = {}
) -> transformers.modeling_outputs.CausalLMOutputWithPast

Forward pass returning CausalLMOutputWithPast.

Parameters:

input_ids

torch.Tensor

Input token IDs. BSHD: [B, S]; THD: [1, T] (squeezed internally).

position_ids

torch.Tensor | NoneDefaults to None

Optional position indices.

attention_mask

torch.Tensor | NoneDefaults to None

Optional attention mask.

padding_mask

torch.Tensor | NoneDefaults to None

Optional padding mask.

logits_to_keep

Union[int, torch.Tensor]Defaults to 0

If 0, compute logits for all positions (training default); otherwise only compute logits for the last logits_to_keep token positions.

output_hidden_states

bool | NoneDefaults to None

Whether to return the final hidden states on the output.

**attn_kwargs

AnyDefaults to {}

Additional arguments forwarded to the base model (e.g. qkv_format).

Returns: CausalLMOutputWithPast

class:~transformers.modeling_outputs.CausalLMOutputWithPast with logits

nemo_automodel.components.models.minimax_m2.model.MiniMaxM2ForCausalLM.from_config(
    config: typing.Any,
    moe_config: nemo_automodel.components.moe.layers.MoEConfig | None = None,
    backend: nemo_automodel.components.models.common.BackendConfig | None = None,
    kwargs = {}
)

classmethod

nemo_automodel.components.models.minimax_m2.model.MiniMaxM2ForCausalLM.from_pretrained(
    pretrained_model_name_or_path: str,
    model_args = (),
    kwargs = {}
)

classmethod

nemo_automodel.components.models.minimax_m2.model.MiniMaxM2ForCausalLM.get_input_embeddings()

nemo_automodel.components.models.minimax_m2.model.MiniMaxM2ForCausalLM.get_output_embeddings()

nemo_automodel.components.models.minimax_m2.model.MiniMaxM2ForCausalLM.initialize_weights(
    buffer_device: torch.device | None = None,
    dtype: torch.dtype = torch.bfloat16
) -> None

nemo_automodel.components.models.minimax_m2.model.MiniMaxM2ForCausalLM.set_input_embeddings(
    value
)

nemo_automodel.components.models.minimax_m2.model.MiniMaxM2ForCausalLM.set_output_embeddings(
    new_embeddings
)

class nemo_automodel.components.models.minimax_m2.model.MiniMaxM2Model(
    config: typing.Any,
    backend: nemo_automodel.components.models.common.BackendConfig,
    moe_config: nemo_automodel.components.moe.layers.MoEConfig | None = None,
    moe_overrides: dict | None = None
)

Bases: Module

embed_tokens

head_dim

layers

= torch.nn.ModuleDict()

max_seq_len

= config.max_position_embeddings

moe_config

= moe_config or MoEConfig(**moe_defaults)

norm

rotary_emb

nemo_automodel.components.models.minimax_m2.model.MiniMaxM2Model.forward(
    input_ids: torch.Tensor,
    position_ids: torch.Tensor | None = None,
    attention_mask: torch.Tensor | None = None,
    padding_mask: torch.Tensor | None = None,
    attn_kwargs: typing.Any = {}
) -> torch.Tensor

nemo_automodel.components.models.minimax_m2.model.MiniMaxM2Model.init_weights(
    buffer_device: torch.device | None = None
) -> None

nemo_automodel.components.models.minimax_m2.model.ModelClass = MiniMaxM2ForCausalLM