{
  "architectures": [
    "ArtemisVLMForConditionalGeneration"
  ],
  "dtype": "bfloat16",
  "image_token_id": 22,
  "model_type": "artemis_vlm",
  "projector_hidden_act": "gelu",
  "text_config": {
    "_name_or_path": "/home/jupyter/schneewolf-a1/A2-ep1-loadable",
    "architectures": [
      "MistralForCausalLM"
    ],
    "attention_dropout": 0.0,
    "bos_token_id": 1,
    "dtype": "bfloat16",
    "eos_token_id": 4,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 5120,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "max_position_embeddings": 131072,
    "model_type": "mistral",
    "num_attention_heads": 32,
    "num_hidden_layers": 40,
    "num_key_value_heads": 8,
    "pad_token_id": null,
    "rms_norm_eps": 1e-05,
    "rope_parameters": {
      "rope_theta": 1000000.0,
      "rope_type": "default"
    },
    "sliding_window": null,
    "tie_word_embeddings": false,
    "use_cache": false,
    "vocab_size": 131072
  },
  "transformers_version": "5.8.0",
  "use_cache": false,
  "video_token_id": 23,
  "vision_config": {
    "deepstack_visual_indexes": [
      5,
      11,
      17
    ],
    "depth": 24,
    "dtype": "bfloat16",
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1024,
    "in_channels": 3,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "model_type": "qwen3_vl_vision",
    "num_heads": 16,
    "num_position_embeddings": 2304,
    "out_hidden_size": 2048,
    "patch_size": 16,
    "spatial_merge_size": 2,
    "temporal_patch_size": 2
  }
}