config.json

{
  "add_cross_attention" : 0,
  "architectures" : [
    "LlavaQwen2ForCausalLM"
  ],
  "attention_dropout" : 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,
  "do_sample" : 0,
  "dtype" : "bfloat16",
  "early_stopping" : 0,
  "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" : 0,
  "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" : 0,
  "is_encoder_decoder" : 0,
  "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,
  "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" : 0,
  "mm_use_im_start_end" : 0,
  "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" : 0,
  "output_hidden_states" : 0,
  "output_scores" : 0,
  "pad_token_id" : null,
  "prefix" : null,
  "problem_type" : null,
  "pruned_heads" : {

  },
  "quantization" : {
    "bits" : 4,
    "group_size" : 64,
    "mode" : "affine"
  },
  "quantization_config" : {
    "bits" : 4,
    "group_size" : 64,
    "mode" : "affine"
  },
  "remove_invalid_values" : 0,
  "repetition_penalty" : 1,
  "return_dict" : 1,
  "return_dict_in_generate" : 0,
  "rms_norm_eps" : 9.9999999999999995e-07,
  "rope_scaling" : null,
  "rope_theta" : 1000000,
  "sep_token_id" : null,
  "sliding_window" : null,
  "suppress_tokens" : null,
  "task_specific_params" : null,
  "temperature" : 1,
  "tf_legacy_loss" : 0,
  "tie_encoder_decoder" : 0,
  "tie_word_embeddings" : 1,
  "tokenizer_class" : null,
  "tokenizer_model_max_length" : 8192,
  "tokenizer_padding_side" : "right",
  "top_k" : 50,
  "top_p" : 1,
  "torchscript" : 0,
  "transformers_version" : "4.56.1",
  "tune_mm_mlp_adapter" : 0,
  "typical_p" : 1,
  "unfreeze_mm_vision_tower" : 1,
  "use_bfloat16" : 0,
  "use_cache" : 1,
  "use_mm_proj" : 1,
  "use_sliding_window" : 0,
  "vision_config" : {
    "cls_ratio" : 2,
    "down_patch_size" : 7,
    "down_stride" : 2,
    "downsamples" : [
      1,
      1,
      1,
      1,
      1
    ],
    "embed_dims" : [
      96,
      192,
      384,
      768,
      1536
    ],
    "hidden_size" : 1024,
    "image_size" : 1024,
    "intermediate_size" : 3072,
    "layer_scale_init_value" : 1.0000000000000001e-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
}