config.json

{
  "architectures": [
    "NandiForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_nandi.NandiConfig",
    "AutoModel": "modeling_nandi.NandiModel",
    "AutoModelForCausalLM": "modeling_nandi.NandiForCausalLM"
  },
  "model_type": "nandi",
  "vocab_size": 131072,
  "hidden_size": 1248,
  "intermediate_size": 3556,
  "num_hidden_layers": 28,
  "num_attention_heads": 16,
  "num_key_value_heads": 8,
  "head_dim": 78,
  "hidden_act": "silu",
  "max_position_embeddings": 2048,
  "initializer_range": 0.02,
  "rms_norm_eps": 1e-06,
  "use_cache": true,
  "pad_token_id": null,
  "bos_token_id": 1,
  "eos_token_id": 0,
  "tie_word_embeddings": true,
  "rope_parameters": {
    "rope_theta": 1000000.0
  },
  "attention_bias": false,
  "attention_dropout": 0.0,
  "mlp_bias": false,
  "factorized_embedding": false,
  "embedding_rank": 768,
  "layer_sharing": false,
  "layer_sharing_repeats": 2,
  "qk_norm": true,
  "shared_kv": true,
  "kv_cache_mode": "shared",
  "torch_dtype": "bfloat16"
}