Upload folder using huggingface_hub

config.json

@@ -0,0 +1,120 @@
+{
+  "activation_type": "silu",
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "architectures": [
+    "LlavaLladaForMaskedDiffusion"
+  ],
+  "attention_dropout": 0.0,
+  "attention_layer_norm": false,
+  "attention_layer_norm_with_affine": true,
+  "auto_map": {
+    "AutoConfig": "configuration_llada.LLaDAConfig",
+    "AutoModel": "modeling_llada.LLaDAModelLM",
+    "AutoModelForCausalLM": "modeling_llada.LLaDAModelLM"
+  },
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "llama",
+  "d_model": 4096,
+  "d_model_gen": 2048,
+  "downsample": true,
+  "dual_tower": true,
+  "dual_tower_layers": 16,
+  "effective_n_kv_heads": 32,
+  "embedding_dropout": 0.0,
+  "embedding_size": 127378,
+  "enc_use_image_branch": true,
+  "eos_token_id": 126081,
+  "faster_token_stride": 10,
+  "flash_attention": false,
+  "force_sample": false,
+  "gen_mlp_type": "dit2",
+  "image_aspect_ratio": "anyres",
+  "image_crop_resolution": null,
+  "image_enc_drop_rate": 0.5,
+  "image_grid_pinpoints": [
+    [
+      384,
+      768
+    ],
+    [
+      768,
+      384
+    ],
+    [
+      768,
+      768
+    ],
+    [
+      1152,
+      384
+    ],
+    [
+      384,
+      1152
+    ]
+  ],
+  "image_split_resolution": null,
+  "include_bias": false,
+  "include_qkv_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "input_emb_norm": false,
+  "layer_norm_type": "rms",
+  "layer_norm_with_affine": true,
+  "mask_token_id": 126336,
+  "max_sequence_length": 4096,
+  "mlp_hidden_size": 12288,
+  "mlp_hidden_size_gen": 8192,
+  "mlp_ratio": 4,
+  "mm_hidden_size": 1152,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "spatial_unpad",
+  "mm_pooler_ratio": 2,
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": "spatial_pool",
+  "mm_spatial_pool_mode": "conv",
+  "mm_spatial_pool_out_channels": 1152,
+  "mm_spatial_pool_stride": 2,
+  "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_vision_resampler,mm_language_model,mm_language_model_vision_parms",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "google/siglip-so400m-patch14-384",
+  "mm_vision_tower_lr": 2e-06,
+  "mm_vqvae": "jacklishufan/LaViDa-O-v1.0",
+  "model_type": "llada",
+  "multi_query_attention": null,
+  "n_heads": 32,
+  "n_kv_heads": 32,
+  "n_layers": 32,
+  "pad_token_id": 126081,
+  "pos_skipping_range": 4096,
+  "precision": "amp_bf16",
+  "prompt_drop_rate": 0.1,
+  "resampler_type": null,
+  "residual_dropout": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope": true,
+  "rope_full_precision": true,
+  "rope_theta": 500000.0,
+  "scale_logits": false,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.3",
+  "use_cache": false,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "vision_tower_pretrained": null,
+  "vocab_size": 127378,
+  "weight_tying": false
+}

configuration_llada.py

@@ -0,0 +1,463 @@
+"""
+LLaDA configuration
+"""
+from transformers import AutoConfig, PretrainedConfig
+
+from enum import Enum
+from os import PathLike
+from typing import Union
+from dataclasses import asdict, dataclass, field
+from glob import glob
+from pathlib import Path
+from typing import (
+    Any,
+    Dict,
+    Iterable,
+    List,
+    Optional,
+    Tuple,
+    Type,
+    TypeVar,
+    Union,
+    cast,
+)
+
+
+__all__ = [
+    "ActivationType",
+    "ActivationCheckpointingStrategy",
+    "BlockType",
+    "LayerNormType",
+    "InitFnType",
+    "ModelConfig",
+]
+
+PathOrStr = Union[str, PathLike]
+
+
+class StrEnum(str, Enum):
+    """
+    This is equivalent to Python's :class:`enum.StrEnum` since version 3.11.
+    We include this here for compatibility with older version of Python.
+    """
+
+    def __str__(self) -> str:
+        return self.value
+
+    def __repr__(self) -> str:
+        return f"'{str(self)}'"
+
+
+class LayerNormType(StrEnum):
+    default = "default"
+    """
+    The default LayerNorm implementation, equivalent to PyTorch's built-in version.
+    """
+
+    low_precision = "low_precision"
+    """
+    A low-precision version of the default LayerNorm.
+    """
+
+    rms = "rms"
+    """
+    An RMSNorm implementation. When using ``torch.compile`` this is
+    probably the fastest implementation.
+    """
+
+    gemma_rms = "gemma_rms"
+    """
+    An RMSNorm implementation by gemmma. When using ``torch.compile`` this is
+    probably the fastest implementation.
+    """
+
+    amd_compatible = "amd_compatible"
+    """
+    LayerNorm implemented manually to work around an issue with ROCm.
+    """
+
+
+class ActivationType(StrEnum):
+    gelu = "gelu"
+    relu = "relu"
+    silu = "silu"
+    swiglu = "swiglu"
+
+
+class BlockType(StrEnum):
+    sequential = "sequential"
+    parallel = "parallel"
+
+    llama = "llama"
+    """
+    A block similar to the sequential block with slightly different
+    implementations of operations like attention to imitate the behavior of Llama.
+    """
+
+
+class InitFnType(StrEnum):
+    mitchell = "mitchell"
+    """
+    The strategy suggested to us by Mitchell Wortsman from UW.
+    This uses a truncated normal distribution with an adaptive standard deviation that depends
+    on the size of the weights as well as the depth of the layer.
+    """
+
+    normal = "normal"
+    """
+    All weights are initialized from the same normal distribution.
+    """
+
+    kaiming_normal = "kaiming_normal"
+    """
+    All weights are initialized with the Kaiming method from a normal distribution.
+    Note this currently won't work with FSDP.
+    """
+
+    fan_in = "fan_in"
+    """
+    "Fan-in variance scaling", i.e. normal with a standard deviation of ``1/sqrt(d_in)`` where ``d_in``
+    is the input dimensionality of the kernel.
+    """
+
+    full_megatron = "full_megatron"
+    """
+    This is what metaseq calls "full megatron init". It is the init used for Llama 2.
+    """
+
+
+@dataclass
+class ModelConfig():
+    """
+    LLaDA (model) configuration.
+    """
+
+    # Note that the defaults for these attributes are equivalent to the base GPT2 model.
+
+    d_model: int = 768
+    """
+    The hidden size of the model.
+    """
+
+    n_heads: int = 12
+    """
+    The number of self-attention heads.
+    """
+
+    n_kv_heads: Optional[int] = None
+    """
+    The number of heads to use for keys and values. Defaults to `n_heads`.
+    Set this to ``None`` or ``n_heads`` for normal multi-head attention.
+    Set this to 1 for multi-query attention.
+    Set it to some in-between value for Llama2-style grouped query attention.
+    """
+
+    n_layers: int = 12
+    """
+    The number of layers/blocks.
+    """
+
+    mlp_ratio: int = 4
+    """
+    The ratio of the inner MLP dimensionality to ``d_model``.
+    This is only used when ``mlp_hidden_size`` is not set.
+    """
+
+    mlp_hidden_size: Optional[int] = None
+    """
+    Set the exact hidden size for the MLP. Otherwise the inner MLP hidden size will be set to `mlp_ratio * d_model`.
+    """
+
+    activation_type: ActivationType = ActivationType.swiglu
+    """
+    The activation function to use within the MLP layers.
+    """
+
+    block_type: BlockType = BlockType.sequential
+    """
+    The transformer block implementation.
+    """
+
+    block_group_size: int = 1
+    """
+    The number of blocks to group together into a single parent block.
+    This has no affect on the number of parameters in the model and is only used to wrap groups
+    of blocks together with a single FSDP wrapper during training.
+    """
+
+    alibi: bool = False
+    """
+    If ``True``, use ALiBi embeddings. Mutually exclusive with ``rope``.
+    """
+
+    alibi_bias_max: float = 8.0
+    """
+    Maximum absolute value of ALiBi bias.
+    """
+
+    rope: bool = False
+    """
+    Use rotary positional embeddings (RoPE). Mutually exclusive with ``alibi``.
+    """
+
+    rope_full_precision: bool = True
+    """
+    If ``True``, apply RoPE embeddings at full precision regardless of the input type. Otherwise,
+    apply RoPE at the precision of the input.
+    """
+
+    flash_attention: bool = False
+    """
+    If ``True``, use ``FlashAttention``.
+    """
+
+    attention_dropout: float = 0.1
+    """
+    The dropout probability within the attention modules.
+    """
+
+    multi_query_attention: Optional[bool] = None
+    """
+    Use the Multi-Query formulation of attention used in PaLM. This reduces the number of parameters
+    and is more efficient during inference.
+    """
+
+    attention_layer_norm: bool = False
+    """
+    Apply layer norm to the keys and queries within the attention mechanism.
+    This can help stabilize training.
+    """
+
+    residual_dropout: float = 0.1
+    """
+    The dropout probability for the MLP and attention output within each block.
+    """
+
+    embedding_dropout: float = 0.1
+    """
+    The dropout probability for embeddings.
+    """
+
+    input_emb_norm: bool = False
+    """
+    An input hidden_states norm implementation by gemmma.
+    """
+
+    layer_norm_type: LayerNormType = LayerNormType.default
+    """
+    The layernorm implementation to use.
+    """
+
+    layer_norm_with_affine: bool = True
+    """
+    Whether to include bias and weight parameters for the layer norms.
+    This only affects layer norms that are immediately followed by a linear layer in the forward pass,
+    so everything except QK-norms. To turn off affines for QK norms as well, set :attr:`attention_layer_norm_with_affine`
+    to ``False``.
+    """
+
+    rms_norm_eps: float = 1e-05
+    """
+    The rms layernorm eps param.
+    """
+
+    attention_layer_norm_with_affine: bool = True
+    """
+    Toggle affine transform for the QK norms.
+    """
+
+    max_sequence_length: int = 1024
+    """
+    The maximum input sequence length supported by the model.
+    """
+
+    rope_theta: float = 10000.0
+    """
+    The rope base param.
+    """
+
+    include_qkv_bias: Optional[bool] = False
+    """
+    Whether or not to include bias parameters in qkv linear layers.
+    """
+
+    include_bias: bool = False
+    """
+    Whether or not to include bias parameters in linear layers.
+    In PaLM, they got rid of all bias terms because they found that large
+    models tend to have near 0 bias terms anyway.
+    """
+
+    bias_for_layer_norm: Optional[bool] = None
+    """
+    Whether or not to include bias parameters in layer norm.
+    This is separate from the include_bias parameter, because of a ROCm crash when biases are disabled in
+    layer norm.
+    When this is None (the default), it inherits the setting from include_bias.
+    """
+
+    scale_logits: bool = False
+    """
+    If ``True``, scale the output logits by ``1 / sqrt(d_model)``.
+    """
+
+    vocab_size: int = 50257
+    """
+    Vocabulary size of the model.
+    """
+
+    embedding_size: Optional[int] = 50304
+    """
+    The number of embeddings, i.e. the number of tokens. If set to ``None`` it will default
+    to ``vocab_size``. If ``vocab_size`` is not a multiple of 128, setting this to the
+    next multiple of 128 that's greater than ``vocab_size`` can improve throughput
+    substantially.
+    """
+
+    weight_tying: bool = True
+    """
+    Whether to tie output linear weights to the input embedding.
+    """
+
+    eos_token_id: int = 50256
+    """
+    The ID of the end-of-sentence special token.
+    """
+
+    pad_token_id: int = 50256
+    """
+    The ID of the token to use for padding. Defaults to the ID of the EOS token.
+    """
+
+    mask_token_id: Optional[int] = 50256
+    """
+    The ID of the token to use for mask token. Defaults to the ID of the EOS token.
+    """
+
+    init_device: Optional[str] = None
+    """
+    The torch device to use when initializing the model parameters, e.g. "cpu", "cuda:0", "meta".
+    """
+
+    init_fn: InitFnType = InitFnType.normal
+    """
+    The weight initialization strategy.
+    """
+
+    init_std: float = 0.02
+    """
+    The standard deviation to use when initializing weights with a "fixed distribution" ``init_fn``, such
+    as "normal".
+    """
+
+    init_cutoff_factor: Optional[float] = None
+    """
+    A positive factor used to scale the cutoff values when initializing weights with a "fixed distribution" ``init_fn``, such
+    as "normal". Setting this to None means values are not cutoff.
+    """
+
+    precision: Optional[str] = None
+    """
+    Precision used to train/evaluate with. You shouldn't set this directly.
+    See :data:`TrainConfig.precision` instead.
+    """
+
+    @property
+    def effective_n_kv_heads(self) -> int:
+        if self.n_kv_heads is None:
+            if self.multi_query_attention is True:
+                return 1
+            else:
+                return self.n_heads
+        else:
+            if self.multi_query_attention is None:
+                return self.n_kv_heads
+            if self.multi_query_attention:
+                n_kv_heads_should_be = 1
+            else:
+                n_kv_heads_should_be = self.n_heads
+            if self.n_kv_heads == n_kv_heads_should_be:
+                return n_kv_heads_should_be
+            else:
+                raise Exception(
+                    "You can't set `multi_query_attention` and `n_kv_heads` at the same time."
+                )
+
+class ActivationCheckpointingStrategy(StrEnum):
+    whole_layer = "whole_layer"
+    """
+    Checkpoint every transformer layer.
+    """
+
+    one_in_two = "one_in_two"
+    """
+    Checkpoint one in two transformer layers.
+    """
+
+    one_in_three = "one_in_three"
+    """
+    Checkpoint one in three transformer layers.
+    """
+
+    one_in_four = "one_in_four"
+    """
+    Checkpoint one in four transformer layers.
+    """
+    
+    two_in_three = "two_in_three"
+    """
+    Checkpoint two out of every three transformer layers.
+    """
+
+    three_in_four = "three_in_four"
+    """
+    Checkpoint three out of four of every transformer layers.
+    """
+
+    four_in_five = "four_in_five"
+    """
+    Checkpoint four out of five of every transformer layers.
+    """
+
+    nine_in_ten = "nine_in_ten"
+    """
+    Checkpoint nine out of ten of every transformer layers.
+    """
+
+    fine_grained = "fine_grained"
+    """
+    Focus checkpointing on where it is cheap to recompute and saves most memory.
+    """
+
+
+class LLaDAConfig(PretrainedConfig):
+    model_type = "llada"
+    keys_to_ignore_at_inference = ["past_key_values"]  # TODO: confirm
+
+    def __init__(self, use_cache: bool = False, **kwargs):
+        model_config = ModelConfig()
+        all_kwargs = model_config.__dict__
+        all_kwargs.update(kwargs)
+        all_kwargs.update({"use_cache": use_cache})
+        all_kwargs.update(
+            {
+                "architectures": all_kwargs.get("architectures", ["LLaDAModelLM"])
+            }
+        )
+        super().__init__(**all_kwargs)
+
+    @property
+    def num_attention_heads(self):
+        return self.n_heads
+
+    @property
+    def num_hidden_layers(self):
+        return self.n_layers
+
+    @property
+    def hidden_size(self):
+        return self.d_model
+
+
+# Register the config class so that it is available for transformer pipelines, auto-loading etc.
+AutoConfig.register("llada", LLaDAConfig)

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 126080,
+  "eos_token_id": 126081,
+  "transformers_version": "4.50.3"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6065a51ca625b72c2e9737880831fe089d048c5a351970dc11ca412d546db5a
+size 4902434136

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e82a3d09a77a044c3f74e4df640a88ebe9230057adaf7cc838c6f54b442cf810
+size 4983055840

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:897b6186718a7e630c7208ee16398bb614151e00af51663a5aee107c2c3383d6
+size 4999840880

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f3e00fafac0766d50906a2e36aed06052bd8351c43706ae87017ed13f89a636
+size 4949501344

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5eea07fd296b73eb2a2293e5f96f8d77f9c87ab2328be4019be81b00ce7cd2
+size 2354041750

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:933f2aea7d59600ea0f07d1ff3b265ce1325367dd5973f7a0c2b6558a1de89c8
+size 9528

vqvae/config.json

@@ -0,0 +1,39 @@
+{
+  "_class_name": "VQModel",
+  "_diffusers_version": "0.30.2",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    256,
+    512,
+    768
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 64,
+  "layers_per_block": 2,
+  "lookup_from_codebook": true,
+  "mid_block_add_attention": false,
+  "norm_num_groups": 32,
+  "norm_type": "group",
+  "num_vq_embeddings": 8192,
+  "out_channels": 3,
+  "sample_size": 32,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "vq_embed_dim": null,
+  "force_upcast": true
+}

vqvae/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62ac839c4caebd5221d3c69a26ae76c057a2bb5b34ac59acec2e48ce4b9ae0a8
+size 292520582

vqvae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1241a5c88b635af4f8cfb268e388ccaa70f55a458a473d68943e5c28d7b7f762
+size 585009980