|
|
| |
| from transformers.configuration_utils import PretrainedConfig, layer_type_validation |
| from transformers.modeling_rope_utils import rope_config_validation |
|
|
|
|
| class Fast_dVLMVisionConfig(PretrainedConfig): |
| model_type = "fast_dvlm" |
| base_config_key = "vision_config" |
|
|
| def __init__( |
| self, |
| depth=32, |
| hidden_size=3584, |
| hidden_act="silu", |
| intermediate_size=3420, |
| num_heads=16, |
| in_channels=3, |
| patch_size=14, |
| spatial_merge_size=2, |
| temporal_patch_size=2, |
| tokens_per_second=4, |
| window_size=112, |
| out_hidden_size=3584, |
| fullatt_block_indexes=[7, 15, 23, 31], |
| initializer_range=0.02, |
| **kwargs, |
| ): |
| super().__init__(**kwargs) |
|
|
| self.depth = depth |
| self.hidden_size = hidden_size |
| self.hidden_act = hidden_act |
| self.intermediate_size = intermediate_size |
| self.num_heads = num_heads |
| self.in_channels = in_channels |
| self.patch_size = patch_size |
| self.spatial_merge_size = spatial_merge_size |
| self.temporal_patch_size = temporal_patch_size |
| self.tokens_per_second = tokens_per_second |
| self.window_size = window_size |
| self.fullatt_block_indexes = fullatt_block_indexes |
| self.out_hidden_size = out_hidden_size |
| self.initializer_range = initializer_range |
|
|
|
|
| class Fast_dVLMTextConfig(PretrainedConfig): |
|
|
| model_type = "fast_dvlm_for_causal_lm" |
| base_config_key = "text_config" |
| keys_to_ignore_at_inference = ["past_key_values"] |
| base_model_tp_plan = { |
| "layers.*.self_attn.q_proj": "colwise", |
| "layers.*.self_attn.k_proj": "colwise", |
| "layers.*.self_attn.v_proj": "colwise", |
| "layers.*.self_attn.o_proj": "rowwise", |
| "layers.*.mlp.gate_proj": "colwise", |
| "layers.*.mlp.up_proj": "colwise", |
| "layers.*.mlp.down_proj": "rowwise", |
| } |
| base_model_pp_plan = { |
| "embed_tokens": (["input_ids"], ["inputs_embeds"]), |
| "layers": (["hidden_states", "attention_mask"], ["hidden_states"]), |
| "norm": (["hidden_states"], ["hidden_states"]), |
| } |
|
|
| def __init__( |
| self, |
| vocab_size=152064, |
| hidden_size=8192, |
| intermediate_size=29568, |
| num_hidden_layers=80, |
| num_attention_heads=64, |
| num_key_value_heads=8, |
| hidden_act="silu", |
| max_position_embeddings=32768, |
| initializer_range=0.02, |
| rms_norm_eps=1e-05, |
| use_cache=True, |
| tie_word_embeddings=False, |
| rope_theta=1000000.0, |
| use_sliding_window=False, |
| sliding_window=4096, |
| max_window_layers=80, |
| layer_types=None, |
| attention_dropout=0.0, |
| rope_scaling=None, |
| image_token_id=None, |
| video_token_id=None, |
| bd_size=8, |
| self_spec_inference_mode=None, |
| block_length=None, |
| use_block_causal_mask=False, |
| complementary_mask=True, |
| minimum_noise_level=1e-3, |
| entropy_loss=False, |
| entropy_loss_weight=1.0, |
| block_causal_no_dynamic=False, |
| **kwargs, |
| ): |
| self.vocab_size = vocab_size |
| self.max_position_embeddings = max_position_embeddings |
| self.hidden_size = hidden_size |
| self.intermediate_size = intermediate_size |
| self.num_hidden_layers = num_hidden_layers |
| self.num_attention_heads = num_attention_heads |
| self.use_sliding_window = use_sliding_window |
| self.sliding_window = sliding_window if self.use_sliding_window else None |
| self.max_window_layers = max_window_layers |
|
|
| |
| if num_key_value_heads is None: |
| num_key_value_heads = num_attention_heads |
|
|
| self.num_key_value_heads = num_key_value_heads |
| self.hidden_act = hidden_act |
| self.initializer_range = initializer_range |
| self.rms_norm_eps = rms_norm_eps |
| self.use_cache = use_cache |
| self.rope_theta = rope_theta |
| self.attention_dropout = attention_dropout |
| self.rope_scaling = rope_scaling |
| self.bd_size = bd_size |
| self.layer_types = layer_types |
| self.use_block_causal_mask = use_block_causal_mask |
| self.complementary_mask = complementary_mask |
| self.minimum_noise_level = minimum_noise_level |
| self.entropy_loss = entropy_loss |
| self.entropy_loss_weight = entropy_loss_weight |
| self.block_causal_no_dynamic = block_causal_no_dynamic |
| self.self_spec_inference_mode = self_spec_inference_mode |
| self.block_length = block_length |
| if self.layer_types is None: |
| self.layer_types = [ |
| "sliding_attention" |
| if self.sliding_window is not None and i >= self.max_window_layers |
| else "full_attention" |
| for i in range(self.num_hidden_layers) |
| ] |
| layer_type_validation(self.layer_types) |
|
|
| |
| |
| |
| |
| |
| if self.rope_scaling is not None and "type" in self.rope_scaling: |
| if self.rope_scaling["type"] == "mrope": |
| self.rope_scaling["type"] = "default" |
| self.rope_scaling["rope_type"] = self.rope_scaling["type"] |
| rope_config_validation(self, ignore_keys={"mrope_section"}) |
| self.image_token_id = image_token_id |
| self.video_token_id = video_token_id |
| super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs) |
|
|
|
|
| class Fast_dVLMConfig(PretrainedConfig): |
|
|
| model_type = "fast_dvlm" |
| sub_configs = {"vision_config": Fast_dVLMVisionConfig, "text_config": Fast_dVLMTextConfig} |
| keys_to_ignore_at_inference = ["past_key_values"] |
|
|
| def __init__( |
| self, |
| text_config=None, |
| vision_config=None, |
| image_token_id=151655, |
| video_token_id=151656, |
| enable_efficient_vision_embed=False, |
| **kwargs, |
| ): |
| if isinstance(vision_config, dict): |
| self.vision_config = self.sub_configs["vision_config"](**vision_config) |
| elif vision_config is None: |
| self.vision_config = self.sub_configs["vision_config"]() |
|
|
| if isinstance(text_config, dict): |
| self.text_config = self.sub_configs["text_config"](**text_config) |
| elif text_config is None: |
| |
| self.text_config = self.sub_configs["text_config"](**kwargs) |
|
|
| self.image_token_id = image_token_id |
| self.video_token_id = video_token_id |
| self.enable_efficient_vision_embed = enable_efficient_vision_embed |
|
|
| super().__init__(**kwargs) |
|
|
|
|
| __all__ = ["Fast_dVLMConfig", "Fast_dVLMTextConfig"] |
