config.json

{
    "architectures": [
        "YuanForCausalLM"
    ],
    "auto_map":{
        "AutoConfig":"configuration_yuan.YuanConfig",
        "AutoModelForCausalLM":"yuan_hf_model.YuanForCausalLM"
    },
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 8192,
    "max_position_embeddings": 8192,
    "model_type": "yuan",
    "num_attention_heads": 32,
    "num_hidden_layers": 24,
    "rms_norm_eps": 1e-06,
    "dropout": 0.1,
    "tie_word_embeddings": true,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.30.0.dev0",
    "use_cache": false,
    "causal_mask": true,
    "use_flash_attention": false,
    "reset_attention_mask": true,
    "reset_position_ids": true,
    "use_loss_mask": false,
    "eod_token": 77185,
    "sep_token": 77187,
    "eod_token_id": 77185,
    "sep_token_id": 77185,
    "pad_token_id": 77185,
    "bos_token_id": 77185,
    "eos_token_id": 77185,
    "mask_token_id": 77185,
    "vocab_size": 135040
}