params.json

{
  "dim": 5120,
  "n_layers": 40,
  "head_dim": 128,
  "hidden_dim": 14336,
  "n_heads": 32,
  "n_kv_heads": 8,
  "rope_theta": 1000000000.0,
  "norm_eps": 1e-05,
  "vocab_size": 131072,
  "vision_encoder": {
    "hidden_size": 1024,
    "num_channels": 3,
    "image_size": 1024,
    "patch_size": 16,
    "rope_theta": 10000.0,
    "intermediate_size": 4096,
    "num_hidden_layers": 24,
    "num_attention_heads": 16,
    "image_token_id": 10
  }
}