config.json

{
  "_name_or_path": "Math-PUMA_Qwen2VL-1.5B",
  "architectures": [
    "Qwen2vlmForConditionalGeneration"
  ],
  "ignore_index": -100,
  "image_token_index": 151646,
  "model_type": "qwen2vlm",
  "projector_hidden_act": "gelu",
  "text_config": {
    "_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
    "architectures": [
      "Qwen2ForCausalLM"
    ],
    "bos_token_id": 151643,
    "eos_token_id": 151645,
    "hidden_size": 1536,
    "intermediate_size": 8960,
    "max_position_embeddings": 32768,
    "max_window_layers": 28,
    "model_type": "qwen2",
    "num_attention_heads": 12,
    "num_hidden_layers": 28,
    "num_key_value_heads": 2,
    "rope_theta": 1000000.0,
    "sliding_window": 32768,
    "tie_word_embeddings": true,
    "torch_dtype": "bfloat16",
    "use_sliding_window": false,
    "vocab_size": 151936
  },
  "torch_dtype": "float32",
  "transformers_version": "4.42.0",
  "vision_config": {
    "hidden_size": 1152,
    "image_size": 384,
    "intermediate_size": 4304,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 27,
    "patch_size": 14
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "default"
}