config.json

{
  "_name_or_path": "jadechoghari/ferret-llama",
  "architectures": [
    "FerretLlamaForCausalLM"
  ],
  "auto_map": {
  "AutoConfig": "modeling.FerretConfig",
  "AutoModel": "modeling.FerretLlamaModel",
  "AutoModelForCausalLM": "modeling.FerretLlamaForCausalLM"
  },
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": 128009,
  "freeze_mm_mlp_adapter": false,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "im_region_fea_token": 128257,
  "image_aspect_ratio": "anyres",
  "image_grid_pinpoints": [
    [
      336,
      672
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      1008,
      336
    ],
    [
      336,
      1008
    ]
  ],
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 8192,
  "mm_hidden_size": 1024,
  "mm_patch_merge_type": "spatial",
  "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": "openai/clip-vit-large-patch14-336",
  "mm_vision_tower_lr": null,
  "model_type": "ferret_llama",
  "num_attention_head": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 128256,
  "pretraining_tp": 1,
  "region_geo_sampler": true,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "sampler_pooler_mode": "max",
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 4096,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.39.0",
  "tune_mm_mlp_adapter": false,
  "unfreeze_mm_vision_tower": false,
  "use_cache": true,
  "use_mm_proj": true,
  "vocab_size": 128258
}