params.json

{
  "dim": 12288,
  "n_layers": 88,
  "head_dim": 128,
  "hidden_dim": 28672,
  "n_heads": 96,
  "n_kv_heads": 8,
  "rope_theta": 1000000.0,
  "norm_eps": 1e-05,
  "vocab_size": 131072,
  "tied_embeddings": false,
  "max_position_embeddings": 262144,
  "q_lora_rank": null,
  "qk_rope_head_dim": null,
  "qk_nope_head_dim": null,
  "kv_lora_rank": null,
  "v_head_dim": null,
  "quantization": {
    "qformat_weight": "fp8_e4m3",
    "qscheme_act": "TENSOR"
  },
  "yarn": {
    "original_max_position_embeddings": 4096,
    "factor": 64,
    "apply_scale": true,
    "beta": 4,
    "alpha": 1
  }
}