{ "architectures": [ "LlavaQwen2ForCausalLM" ], "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_llava_qwen2.LlavaQwen2Config", "AutoModelForCausalLM": "modeling_llava_qwen2.LlavaQwen2ForCausalLM" }, "bos_token_id": 151645, "eos_token_id": 151645, "freeze_mm_mlp_adapter": false, "hidden_act": "silu", "hidden_size": 1024, "image_aspect_ratio": "pad", "initializer_range": 0.02, "intermediate_size": 2816, "language_model": "vilm/Quyen-SE-v0.1", "max_position_embeddings": 32768, "max_window_layers": 21, "mm_hidden_size": 1152, "mm_projector_lr": null, "mm_projector_type": "mlp2x_gelu", "mm_vision_tower": "google/siglip-so400m-patch14-384", "model_type": "llava-qwen2", "num_attention_heads": 16, "num_hidden_layers": 24, "num_key_value_heads": 16, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": 4096, "text_config": { "vocab_size": 151936, "max_position_embeddings": 32768, "hidden_size": 1024, "intermediate_size": 2816, "num_hidden_layers": 24, "num_attention_heads": 16, "use_sliding_window": false, "sliding_window": 4096, "max_window_layers": 21, "num_key_value_heads": 16, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-06, "use_cache": false, "rope_theta": 1000000.0, "attention_dropout": 0.0, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": "bfloat16", "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": [ "Qwen2ForCausalLM" ], "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "tokenizer_class": null, "prefix": null, "bos_token_id": null, "pad_token_id": null, "eos_token_id": 151645, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "vilm/Quyen-SE-v0.1", "transformers_version": "4.39.3", "model_type": "qwen2" }, "tie_word_embeddings": false, "tokenizer_model_max_length": 4096, "tokenizer_padding_side": "right", "torch_dtype": "bfloat16", "transformers_version": "4.39.2", "tune_mm_mlp_adapter": false, "use_cache": false, "use_mm_proj": true, "use_sliding_window": false, "vision_config": { "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": null, "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "tokenizer_class": null, "prefix": null, "bos_token_id": null, "pad_token_id": null, "eos_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "model_type": "siglip_vision_model", "hidden_size": 1152, "intermediate_size": 4304, "num_hidden_layers": 27, "num_attention_heads": 16, "num_channels": 3, "patch_size": 14, "image_size": 384, "attention_dropout": 0.0, "layer_norm_eps": 1e-06, "hidden_act": "gelu_pytorch_tanh" }, "vocab_size": 151936 }