{ "_attn_implementation_autoset": true, "_name_or_path": "lmms-lab/llava-onevision-qwen2-0.5b-ov", "architectures": [ "LlavaQwenForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 896, "ignore_index": -100, "image_aspect_ratio": "anyres_max_9", "image_crop_resolution": null, "image_grid_pinpoints": [ [ 384, 384 ], [ 384, 768 ], [ 384, 1152 ], [ 384, 1536 ], [ 384, 1920 ], [ 384, 2304 ], [ 768, 384 ], [ 768, 768 ], [ 768, 1152 ], [ 768, 1536 ], [ 768, 1920 ], [ 768, 2304 ], [ 1152, 384 ], [ 1152, 768 ], [ 1152, 1152 ], [ 1152, 1536 ], [ 1152, 1920 ], [ 1152, 2304 ], [ 1536, 384 ], [ 1536, 768 ], [ 1536, 1152 ], [ 1536, 1536 ], [ 1536, 1920 ], [ 1536, 2304 ], [ 1920, 384 ], [ 1920, 768 ], [ 1920, 1152 ], [ 1920, 1536 ], [ 1920, 1920 ], [ 1920, 2304 ], [ 2304, 384 ], [ 2304, 768 ], [ 2304, 1152 ], [ 2304, 1536 ], [ 2304, 1920 ], [ 2304, 2304 ] ], "image_seq_length": 576, "image_split_resolution": null, "image_token_index": 151646, "initializer_range": 0.02, "intermediate_size": 4864, "max_position_embeddings": 32768, "max_window_layers": 24, "mm_hidden_size": 1152, "mm_newline_position": "one_token", "mm_patch_merge_type": "spatial_unpad", "mm_projector_lr": null, "mm_projector_type": "mlp2x_gelu", "mm_resampler_type": null, "mm_spatial_pool_mode": "bilinear", "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model", "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, "model_type": "llava", "num_attention_heads": 14, "num_hidden_layers": 24, "num_key_value_heads": 2, "pos_skipping_range": 4096, "projector_hidden_act": "gelu", "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": 32768, "text_config": { "_attn_implementation_autoset": false, "_name_or_path": "", "add_cross_attention": false, "architectures": null, "attention_bias": false, "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 1, "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": 2, "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": 4096, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 11008, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 2048, "min_length": 0, "mlp_bias": false, "model_type": "llama", "no_repeat_ngram_size": 0, "num_attention_heads": 32, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 32, "num_key_value_heads": 32, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "pretraining_tp": 1, "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": 10000.0, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 32000 }, "tokenizer_model_max_length": 32768, "tokenizer_padding_side": "right", "torch_dtype": "bfloat16", "transformers_version": "4.46.3", "use_cache": true, "use_mm_proj": true, "use_pos_skipping": false, "use_sliding_window": false, "vision_config": { "_attn_implementation_autoset": false, "_name_or_path": "", "add_cross_attention": false, "architectures": null, "attention_dropout": 0.0, "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, "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, "hidden_act": "quick_gelu", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 336, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-05, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "clip_vision_model", "no_repeat_ngram_size": 0, "num_attention_heads": 16, "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, "problem_type": null, "projection_dim": 768, "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, "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": null, "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "vocab_size": 32000 }, "vision_feature_layer": -2, "vision_feature_select_strategy": "default", "vision_tower_pretrained": null, "vocab_size": 151936 }