last-checkpoint/config.json

{
  "architectures": [
    "CustomVisionTextModel"
  ],
  "logit_scale_init_value": 2.6592,
  "model_type": "vision-text-dual-encoder",
  "projection_dim": 1024,
  "text_config": {
    "_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 128000,
    "eos_token_id": [
      128001,
      128008,
      128009
    ],
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 3072,
    "initializer_range": 0.02,
    "intermediate_size": 8192,
    "max_position_embeddings": 131072,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 24,
    "num_hidden_layers": 28,
    "num_key_value_heads": 8,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": {
      "factor": 32.0,
      "high_freq_factor": 4.0,
      "low_freq_factor": 1.0,
      "original_max_position_embeddings": 8192,
      "rope_type": "llama3"
    },
    "rope_theta": 500000.0,
    "tie_word_embeddings": true,
    "torch_dtype": "bfloat16",
    "use_cache": true,
    "vocab_size": 128256
  },
  "torch_dtype": "float32",
  "transformers_version": "4.52.4",
  "vision_config": {
    "attention_dropout": 0.0,
    "dropout": 0.0,
    "hidden_act": "quick_gelu",
    "hidden_size": 1024,
    "image_size": 336,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "layer_norm_eps": 1e-05,
    "model_type": "clip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "projection_dim": 768
  }
}