params.json

{
  "dim": 5120,
  "n_layers": 40,
  "head_dim": 128,
  "hidden_dim": 32768,
  "n_heads": 32,
  "n_kv_heads": 8,
  "rope_theta": 1000000000.0,
  "norm_eps": 1e-05,
  "vocab_size": 131072,
  "max_position_embeddings": 131072,
  "vision_encoder": {
    "hidden_size": 1024,
    "num_channels": 3,
    "max_image_size": 1540,
    "patch_size": 14,
    "rope_theta": 10000.0,
    "intermediate_size": 4096,
    "num_hidden_layers": 24,
    "num_attention_heads": 16,
    "adapter_bias": false,
    "mm_projector_id": "patch_merge",
    "spatial_merge_size": 2,
    "add_pre_mm_projector_layer_norm": true,
    "image_token_id": 10,
    "image_break_token_id": 12,
    "image_end_token_id": 13,
    "image_size": 1540
  },
  "quantization": {
    "config_groups": {
      "group_0": {
        "input_activations": {
          "dynamic": true,
          "num_bits": 8,
          "observer": null,
          "strategy": "token",
          "symmetric": true,
          "type": "float"
        },
        "targets": [
          "Linear"
        ],
        "weights": {
          "dynamic": false,
          "num_bits": 8,
          "observer": "minmax",
          "strategy": "tensor",
          "symmetric": true,
          "type": "float"
        }
      }
    },
    "format": "float-quantized",
    "ignore": [
      "lm_head",
      "output"
    ],
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed"
  }
}