config.json

{
    "add_cross_attention": false,
    "architectures": [
        "LlavaQwen2ForCausalLM"
    ],
    "attention_dropout": 0.0,
    "auto_map": {
        "AutoConfig": "llava_qwen.LlavaConfig",
        "AutoModelForCausalLM": "llava_qwen.LlavaQwen2ForCausalLM",
        "AutoProcessor": "processing_fastvlm.FastVLMProcessor"
    },
    "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,
    "dtype": "bfloat16",
    "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,
    "freeze_mm_mlp_adapter": false,
    "hidden_act": "silu",
    "hidden_size": 896,
    "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
    },
    "image_aspect_ratio": "pad",
    "image_grid_pinpoints": null,
    "initializer_range": 0.02,
    "intermediate_size": 4864,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
    },
    "layer_types": [
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention"
    ],
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 32768,
    "max_window_layers": 24,
    "min_length": 0,
    "mm_hidden_size": 3072,
    "mm_patch_merge_type": "flat",
    "mm_projector_lr": null,
    "mm_projector_type": "mlp2x_gelu",
    "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": "mobileclip_l_1024",
    "model_type": "llava_qwen2",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 14,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 24,
    "num_key_value_heads": 2,
    "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": 1000000.0,
    "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,
    "tokenizer_model_max_length": 8192,
    "tokenizer_padding_side": "right",
    "top_k": 50,
    "top_p": 1.0,
    "torchscript": false,
    "transformers_version": "4.56.1",
    "tune_mm_mlp_adapter": false,
    "typical_p": 1.0,
    "unfreeze_mm_vision_tower": true,
    "use_bfloat16": false,
    "use_cache": true,
    "use_mm_proj": true,
    "use_sliding_window": false,
    "vision_config": {
        "cls_ratio": 2.0,
        "down_patch_size": 7,
        "down_stride": 2,
        "downsamples": [
            true,
            true,
            true,
            true,
            true
        ],
        "embed_dims": [
            96,
            192,
            384,
            768,
            1536
        ],
        "hidden_size": 1024,
        "image_size": 1024,
        "intermediate_size": 3072,
        "layer_scale_init_value": 1e-05,
        "layers": [
            2,
            12,
            24,
            4,
            2
        ],
        "mlp_ratios": [
            4,
            4,
            4,
            4,
            4
        ],
        "num_classes": 1000,
        "patch_size": 64,
        "pos_embs_shapes": [
            null,
            null,
            null,
            [
                7,
                7
            ],
            [
                7,
                7
            ]
        ],
        "projection_dim": 768,
        "repmixer_kernel_size": 3,
        "token_mixers": [
            "repmixer",
            "repmixer",
            "repmixer",
            "attention",
            "attention"
        ]
    },
    "vocab_size": 151936
}