{ "architectures": [ "ILLUMEForConditionalGeneration" ], "auto_map": { "AutoConfig": "configuration_illume.ILLUMEConfig", "AutoModel": "modeling_illume.ILLUMEForConditionalGeneration", "AutoModelForCausalLM": "modeling_illume.ILLUMEForConditionalGeneration" }, "ignore_index": -100, "image_out_token_index": 282777, "image_token_index": 282776, "mm_projector_config": { "hidden_size": 3584, "mm_hidden_size": [ 3584, 32 ], "projector_cfg1": { "mlp_depth": 2, "type": "MLPProjector" }, "projector_cfg2": { "mlp_depth": 2, "type": "MLPProjector" }, "trainable": true, "type": "MixedProjector" }, "model_type": "illume", "special_tokens_ids": { "": 151666, "": 151669, "": 151671, "": 151667, "": 151665, "": 151668, "": 151670 }, "text_config": { "_name_or_path": "./Qwen2.5-7B-Instruct-with-vision-tokenizer-32k-96k-level2", "architectures": [ "Qwen2ForCausalLM" ], "bos_token_id": 151643, "eos_token_id": 151645, "hidden_size": 3584, "intermediate_size": 18944, "model_type": "qwen2", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rope_theta": 1000000.0, "torch_dtype": "bfloat16", "vocab_size": 283175 }, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.44.2", "vision_config": { "_name_or_path": "./dualvitok/", "architectures": [ "DualViTok" ], "auto_map": { "AutoConfig": "configuration_dualvitok.DualViTokConfig", "AutoModel": "modeling_dualvitok.DualViTok" }, "model_type": "DualViTok", "pixel_decoder": { "attn_resolutions": [ 4 ], "ch": 384, "ch_mult": [ 1, 1, 2, 2, 4 ], "codebook_size": 98304, "embed_dim": 64, "use_dc_up_down_blocks": true, "z_channels": 64 }, "pixel_encoder": { "attn_resolutions": [ 4 ], "ch": 128, "ch_mult": [ 1, 1, 2, 2, 4 ], "codebook_size": 98304, "embed_dim": 32, "use_dc_up_down_blocks": true, "z_channels": 32 }, "semantic_decoder": { "pretrained_semantic_encoder": "Emova-ollm/qwen2vit600m", "target_mlp": "norm" }, "semantic_encoder": { "pretrained_semantic_encoder": { "_name_or_path": "Emova-ollm/qwen2vit600m", "add_cross_attention": false, "architectures": [ "Qwen2VisionTransformerPretrainedModel" ], "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, "depth": 32, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "embed_dim": 1280, "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, "hidden_act": "quick_gelu", "hidden_size": 3584, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "in_channels": 3, "in_chans": 3, "initializer_range": 0.02, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "mlp_ratio": 4, "model_type": "qwen2_vl", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_heads": 16, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "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, "spatial_merge_size": 2, "spatial_patch_size": 14, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "temporal_patch_size": 2, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "float32", "torchscript": false, "transformers_version": "4.44.2", "typical_p": 1.0, "use_bfloat16": false } }, "torch_dtype": "float16" } }