config.json

{
  "_from_model_config": true,
  "architectures": [
    "YuanForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_yuan.YuanConfig",
    "AutoModelForCausalLM": "yuan_hf_model.YuanForCausalLM"
  },
  "bos_token_id": 77185,
  "causal_mask": true,
  "dropout": 0.1,
  "eod_token": 77185,
  "eod_token_id": 77185,
  "eos_token_id": 77185,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 32768,
  "mask_token_id": 77185,
  "max_position_embeddings": 4096,
  "model_max_length": 4096,
  "model_type": "yuan",
  "num_attention_heads": 64,
  "num_hidden_layers": 42,
  "pad_token_id": 77185,
  "reset_attention_mask": true,
  "reset_position_ids": true,
  "rms_norm_eps": 1e-06,
  "sep_token": 77187,
  "sep_token_id": 77185,
  "tokenizer_class": "YuanTokenizer",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.30.2",
  "use_cache": true,
  "use_flash_attention": true,
  "use_loss_mask": false,
  "vocab_size": 135040
}