config.json

{
  "architectures": [
    "LlavaForConditionalGeneration"
  ],
  "dtype": "float32",
  "ignore_index": -100,
  "image_seq_length": 10,
  "image_token_index": 0,
  "model_type": "llava",
  "multimodal_projector_bias": true,
  "projector_hidden_act": "gelu",
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attention_probs_dropout_prob": 0.1,
    "head_dim": 8,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 32,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1",
      "2": "LABEL_2"
    },
    "initializer_range": 0.02,
    "intermediate_size": 37,
    "is_training": true,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1,
      "LABEL_2": 2
    },
    "max_position_embeddings": 512,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 4,
    "num_choices": 4,
    "num_hidden_layers": 2,
    "num_key_value_heads": 4,
    "pad_token_id": 1,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
      "rope_theta": 10000.0,
      "rope_type": "default"
    },
    "seq_length": 7,
    "type_sequence_label_size": 2,
    "type_vocab_size": 16,
    "use_cache": true,
    "use_input_mask": true,
    "use_labels": true,
    "use_token_type_ids": false,
    "vocab_size": 99
  },
  "transformers_version": "5.0.0.dev0",
  "vision_config": {
    "attention_dropout": 0.1,
    "dropout": 0.1,
    "hidden_act": "quick_gelu",
    "hidden_size": 32,
    "image_size": 8,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 37,
    "is_training": true,
    "layer_norm_eps": 1e-05,
    "model_type": "clip_vision_model",
    "num_attention_heads": 4,
    "num_channels": 3,
    "num_hidden_layers": 2,
    "patch_size": 2,
    "projection_dim": 32
  },
  "vision_feature_layer": -1,
  "vision_feature_select_strategy": "default"
}