Nanbeige/config.json

{
  "architectures": [
    "NanbeigeForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_nanbeige.NanbeigeConfig",
    "AutoModel": "modeling_nanbeige.NanbeigeModel",
    "AutoModelForCausalLM": "modeling_nanbeige.NanbeigeForCausalLM"
  },
  "bos_token_id": 166100,
  "eos_token_id": 166101,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 3072,
  "initializer_range": 0.02,
  "intermediate_size": 10752,
  "kv_channels": 128,
  "loop_loss_weights": [],
  "max_length": null,
  "max_position_embeddings": 262144,
  "model_type": "nanbeige",
  "num_attention_heads": 48,
  "num_hidden_layers": 22,
  "num_key_value_heads": 8,
  "num_loops": 2,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 70000000,
  "skip_loop_final_norm": false,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.42.4",
  "use_cache": true,
  "vocab_size": 166144
}