fastvideo.configs.models.encoders.lingbotworld2_t5.TextEncoderArchConfig
TextEncoderArchConfig(stacked_params_mapping: list[tuple[str, str, str]] = list(), architectures: list[str] = (lambda: [])(), _supported_attention_backends: tuple[AttentionBackendEnum, ...] = (AttentionBackendEnum.FLASH_ATTN, AttentionBackendEnum.TORCH_SDPA), output_hidden_states: bool = False, use_return_dict: bool = True, vocab_size: int = 0, hidden_size: int = 0, num_hidden_layers: int = 0, num_attention_heads: int = 0, pad_token_id: int = 0, eos_token_id: int = 0, text_len: int = 0, hidden_state_skip_layer: int = 0, decoder_start_token_id: int = 0, output_past: bool = True, scalable_attention: bool = True, tie_word_embeddings: bool = False, tokenizer_kwargs: dict[str, Any] = dict(), _fsdp_shard_conditions: list = (lambda: [])(), require_processor: bool = False)
fastvideo.configs.models.encoders.lingbotworld2_t5.TextEncoderConfig
TextEncoderConfig(arch_config: ArchConfig = TextEncoderArchConfig(), prefix: str = '', quant_config: QuantizationConfig | None = None, lora_config: Any | None = None, is_chat_model: bool = False, treat_empty_as_dot: bool = False, *, _resolved_attention_backend: AttentionBackendEnum | None = None, chat_template_enable_thinking: bool = False)
fastvideo.configs.models.encoders.lingbotworld2_t5.LingBotWorld2UMT5ArchConfig
LingBotWorld2UMT5ArchConfig(stacked_params_mapping: list[tuple[str, str, str]] = list(), architectures: list[str] = (lambda: ['LingBotWorld2T5EncoderModel'])(), _supported_attention_backends: tuple[AttentionBackendEnum, ...] = (AttentionBackendEnum.FLASH_ATTN, AttentionBackendEnum.TORCH_SDPA), output_hidden_states: bool = False, use_return_dict: bool = True, vocab_size: int = 256384, hidden_size: int = 4096, num_hidden_layers: int = 0, num_attention_heads: int = 0, pad_token_id: int = 0, eos_token_id: int = 0, text_len: int = 512, hidden_state_skip_layer: int = 0, decoder_start_token_id: int = 0, output_past: bool = True, scalable_attention: bool = True, tie_word_embeddings: bool = False, tokenizer_kwargs: dict[str, Any] = dict(), _fsdp_shard_conditions: list = (lambda: [])(), require_processor: bool = False, dim: int = 4096, dim_attn: int = 4096, dim_ffn: int = 10240, num_heads: int = 64, num_layers: int = 24, num_buckets: int = 32, dropout: float = 0.1)
Source
@dataclass
class LingBotWorld2UMT5ArchConfig(TextEncoderArchConfig):
architectures: list[str] = field(default_factory=lambda: ["LingBotWorld2T5EncoderModel"])
vocab_size: int = 256384
dim: int = 4096
dim_attn: int = 4096
dim_ffn: int = 10240
num_heads: int = 64
num_layers: int = 24
num_buckets: int = 32
text_len: int = 512
hidden_size: int = 4096
dropout: float = 0.1
def __post_init__(self) -> None:
super().__post_init__()
self.tokenizer_kwargs = {
"padding": "max_length",
"truncation": True,
"max_length": self.text_len,
"add_special_tokens": True,
"return_attention_mask": True,
"return_tensors": "pt",
}</code></pre></details>
fastvideo.configs.models.encoders.lingbotworld2_t5.LingBotWorld2UMT5Config
LingBotWorld2UMT5Config(arch_config: TextEncoderArchConfig = LingBotWorld2UMT5ArchConfig(), prefix: str = 'text_encoder', quant_config: QuantizationConfig | None = None, lora_config: Any | None = None, is_chat_model: bool = False, treat_empty_as_dot: bool = False, *, _resolved_attention_backend: AttentionBackendEnum | None = None, chat_template_enable_thinking: bool = False)
Source
@dataclass
class LingBotWorld2UMT5Config(TextEncoderConfig):
arch_config: TextEncoderArchConfig = field(default_factory=LingBotWorld2UMT5ArchConfig)
prefix: str = "text_encoder"</code></pre></details>