config.json

{
  "architectures": [
    "TinyEmoForConditionalGeneration"
  ],
  "cache_dir": null,
  "connector_type": "mlp2x_gelu",
  "hidden_size": 1536,
  "ignore_index": -100,
  "image_aspect_ratio": "square",
  "image_token_index": -200,
  "llm_model_name_or_path": "apple/OpenELM-450M-Instruct",
  "model_type": "tinyemo",
  "auto_map": {
    "AutoConfig": "configuration_openelm.OpenELMConfig",
    "AutoModelForCausalLM": "modeling_openelm.OpenELMForCausalLM"
  },
  "num_queries": 128,
  "num_resampler_layers": 3,
  "pad_token": "<|endoftext|>",
  "pad_token_id": 1,
  "resampler_hidden_size": 768,
  "text_config": {
    "_name_or_path": "apple/OpenELM-450M-Instruct",
    "architectures": [
      "OpenELMForCausalLM"
    ],
    "auto_map": {
      "AutoConfig": "configuration_openelm.OpenELMConfig",
      "AutoModelForCausalLM": "modeling_openelm.OpenELMForCausalLM"
    },
    "bos_token_id": 1,
    "eos_token_id": 2,
    "ffn_dim_divisor": 256,
    "ffn_multipliers": [
      0.5, 0.68, 0.87, 1.05, 1.24, 1.42, 1.61, 1.79, 1.97, 2.16, 2.34, 2.53, 2.71, 2.89, 3.08, 3.26, 3.45, 3.63, 3.82, 4.0
    ],
    "ffn_with_glu": true,
    "hidden_act": "swish",
    "head_dim": 64,
    "initializer_range": 0.02,
    "max_context_length": 2048,
    "model_dim": 1536,
    "model_type": "openelm",
    "normalization_layer_name": "rms_norm",
    "normalize_qk_projections": true,
    "num_gqa_groups": 4,
    "num_kv_heads": [
      3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 6, 6, 6, 6
    ],
    "num_query_heads": [
      12, 12, 12, 16, 16, 16, 16, 16, 16, 16, 20, 20, 20, 20, 20, 20, 24, 24, 24, 24
    ],
    "num_transformer_layers": 20,
    "qkv_multipliers": [0.5, 1.0],
    "rope_freq_constant": 10000,
    "rope_max_length": 4096,
    "share_input_output_layers": true,
    "torch_dtype": "bfloat16",
    "vocab_size": 32000
  },
  "tokenizer_model_max_length": 4096,
  "tokenizer_padding_side": "right",
  "tokenizer_use_fast": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.39.3",
  "tune_type_connector": "full",
  "tune_type_llm": "full",
  "tune_type_vision_tower": "frozen",
  "tune_vision_tower_from_layer": 0,
  "use_cache": true,
  "vision_config": {
    "_name_or_path": "openai/clip-vit-large-patch14",
    "architectures": [
      "CLIPModel"
    ],
    "hidden_act": "quick_gelu",
    "hidden_size": 1024,
    "image_size": 224,
    "intermediate_size": 4096,
    "layer_norm_eps": 1e-05,
    "model_type": "clip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "projection_dim": 768
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "patch",
  "vision_hidden_size": 1024,
  "vision_model_name_or_path": "openai/clip-vit-large-patch14",
  "vocab_size": 32000
}