{ "architectures": [ "OvisU1" ], "auto_map": { "AutoConfig": "configuration_ovis_u1.OvisU1Config", "AutoModelForCausalLM": "modeling_ovis_u1.OvisU1" }, "conversation_formatter_class": "Qwen3ConversationFormatter", "disable_tie_weight": false, "hidden_size": 2048, "llm_attn_implementation": null, "llm_config": { "_attn_implementation_autoset": true, "_name_or_path": "Qwen/Qwen3-1.7B", "add_cross_attention": false, "architectures": [ "Qwen3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 151643, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 151645, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 6144, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 40960, "max_window_layers": 28, "min_length": 0, "model_type": "qwen3", "no_repeat_ngram_size": 0, "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 28, "num_key_value_heads": 8, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000, "sep_token_id": null, "sliding_window": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 }, "model_type": "ovis_u1", "multimodal_max_length": 4496, "torch_dtype": "bfloat16", "transformers_version": "4.51.3", "use_cache": false, "visual_generator_config": { "_attn_implementation_autoset": true, "_name_or_path": "yak_1b/yak_1b_qwen3_trained_S8", "add_cross_attention": false, "architectures": [ "YakModel" ], "axes_dim": [ 16, 56, 56 ], "bad_words_ids": null, "base_shift": 0.5, "begin_suppress_tokens": null, "bos_token_id": null, "checkpoint": false, "chunk_size_feed_forward": 0, "context_in_dim": 4096, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "depth": 6, "depth_single_blocks": 12, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "guidance_embed": false, "hidden_size": 1536, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "in_channels": 16, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_shift": 1.15, "min_length": 0, "mlp_ratio": 4.0, "model_type": "yak", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_heads": 12, "num_return_sequences": 1, "out_channels": 16, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "problem_type": null, "pruned_heads": {}, "qkv_bias": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "theta": 10000, "tie_encoder_decoder": false, "tie_word_embeddings": true, "timestep_shift": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "float32", "torchscript": false, "txt_type": "refiner", "typical_p": 1.0, "use_bfloat16": false, "vae_config": { "_class_name": "AutoencoderKL", "_diffusers_version": "0.18.0.dev0", "_name_or_path": ".", "act_fn": "silu", "block_out_channels": [ 128, 256, 512, 512 ], "down_block_types": [ "DownEncoderBlock2D", "DownEncoderBlock2D", "DownEncoderBlock2D", "DownEncoderBlock2D" ], "force_upcast": false, "in_channels": 3, "latent_channels": 4, "layers_per_block": 2, "norm_num_groups": 32, "out_channels": 3, "sample_size": 512, "scaling_factor": 0.13025, "up_block_types": [ "UpDecoderBlock2D", "UpDecoderBlock2D", "UpDecoderBlock2D", "UpDecoderBlock2D" ] }, "vec_in_dim": 1536 }, "visual_tokenizer_config": { "_attn_implementation_autoset": true, "_name_or_path": "", "add_cross_attention": false, "architectures": null, "backbone_config": { "_attn_implementation_autoset": false, "_name_or_path": "aimv2/visual_tokenizer_backbone", "add_cross_attention": false, "architectures": [ "AIMv2Model" ], "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_aimv2.AIMv2Config", "AutoModel": "modeling_aimv2.AIMv2Model", "FlaxAutoModel": "modeling_flax_aimv2.FlaxAIMv2Model" }, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "disable_rope": false, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "fullatt_block_indexes": null, "hidden_size": 1024, "hidden_stride": 2, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 448, "intermediate_size": 2816, "interpolate_pe_method": "two_dim", "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_pixels": 2408448, "min_length": 0, "min_pixels": 200704, "model_type": "aimv2", "no_repeat_ngram_size": 0, "num_attention_heads": 8, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "preserve_original_pe": true, "problem_type": null, "projection_dropout": 0.0, "pruned_heads": {}, "qkv_bias": false, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-05, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "temporal_patch_size": 1, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_bias": false, "window_size": 112 }, "backbone_kwargs": { "disable_rope": false, "hidden_stride": 2, "interpolate_pe_method": "two_dim", "max_pixels": 2408448, "min_pixels": 200704, "preserve_original_pe": true, "temporal_patch_size": 1, "window_size": 112 }, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "depths": null, "disable_rope": false, "diversity_penalty": 0.0, "do_sample": false, "drop_cls_token": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "fullatt_block_indexes": null, "hidden_stride": 2, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_processor_new_kwargs": { "hidden_stride": 2, "max_pixels": 2408448, "min_pixels": 200704, "temporal_patch_size": 1 }, "interpolate_pe_method": "two_dim", "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_pixels": 2408448, "min_length": 0, "min_pixels": 200704, "model_type": "aimv2_visual_tokenizer", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "preserve_original_pe": true, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "tau": 1.0, "temperature": 1.0, "temporal_patch_size": 1, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenize_function": "softmax", "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_indicators": false, "vocab_size": 65536, "window_size": 112 } }