config.json

{
  "architectures": [
    "NanovlmForConditionalGeneration"
  ],
  "image_token_count": 256,
  "image_token_id": 151655,
  "model_type": "nanovlm",
  "projector_hidden_act": "gelu",
  "projector_hidden_size": null,
  "projector_num_layers": 2,
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "eos_token_id": 151645,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 1024,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "max_position_embeddings": 40960,
    "max_window_layers": 28,
    "model_type": "qwen3",
    "num_attention_heads": 16,
    "num_hidden_layers": 28,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 1000000,
    "sliding_window": null,
    "tie_word_embeddings": true,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.51.0",
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 151936
  },
  "transformers_version": "4.57.1",
  "vision_config": {
    "hidden_size": 1152,
    "intermediate_size": 4304,
    "model_type": "siglip2_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 27
  },
  "vision_feature_dim": 1152,
  "vocab_size": 151936
}