config.json

{
  "architectures": [
    "AX4VLForConditionalGeneration"
  ],
  "auto_map": {
    "AutoConfig": "configuration_ax4vl.AX4VLConfig",
    "AutoModelForCausalLM": "modeling_ax4vl.AX4VLForConditionalGeneration",
    "AutoProcessor": "processing_ax4vl.AX4VLProcessor"
  },
  "downsample_ratio": 0.5,
  "dynamic_image_size": true,
  "force_image_size": 384,
  "image_token_index": 22,
  "llm_config": {
    "_attn_implementation_autoset": false,
    "add_cross_attention": false,
    "architectures": [
      "Qwen2ForCausalLM"
    ],
    "attention_dropout": 0.0,
    "attn_implementation": "flash_attention_2",
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 0,
    "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": 0,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "silu",
    "hidden_size": 3584,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 18944,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 16384,
    "max_window_layers": 28,
    "min_length": 0,
    "model_type": "qwen2",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 28,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 28,
    "num_key_value_heads": 4,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 1,
    "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-05,
    "rope_scaling": null,
    "rope_theta": 1000000,
    "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": false,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": "bfloat16",
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": false,
    "use_sliding_window": false,
    "vocab_size": 102400
  },
  "max_dynamic_patch": 12,
  "max_num_tiles": 12,
  "min_dynamic_patch": 1,
  "min_num_tiles": 1,
  "model_type": "a.x-4-vl",
  "pad_token_id": 1,
  "projector_config": {
    "grid_size": 12,
    "in_hidden_size": 1152,
    "model_type": "ldpnetv2_projector",
    "out_hidden_size": 3584,
    "torch_dtype": "bfloat16"
  },
  "ps_version": "v2",
  "select_layer": -1,
  "template": "axvlm",
  "text_config": {
    "architectures": [
      "Qwen2ForCausalLM"
    ],
    "attn_implementation": "flash_attention_2",
    "bos_token_id": 0,
    "eos_token_id": 0,
    "hidden_size": 3584,
    "intermediate_size": 18944,
    "max_position_embeddings": 16384,
    "model_type": "qwen2",
    "num_attention_heads": 28,
    "num_hidden_layers": 28,
    "num_key_value_heads": 4,
    "pad_token_id": 1,
    "rms_norm_eps": 1e-05,
    "rope_theta": 1000000,
    "sliding_window": null,
    "torch_dtype": "bfloat16",
    "use_cache": false,
    "vocab_size": 102400
  },
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.49.0",
  "use_thumbnail": true,
  "vision_config": {
    "drop_path_rate": 0.0,
    "hidden_size": 1152,
    "image_size": 384,
    "intermediate_size": 4304,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 27,
    "torch_dtype": "bfloat16",
    "vision_use_head": false
  },
  "vision_feature_layer": 0,
  "vision_feature_select_strategy": "full"
}