pretrain/config.json

{
  "_name_or_path": "out_f_line/xl_f_line/iter-0550000",
  "architectures": [
    "XModelForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_xmodel.XModelConfig",
    "AutoModelForCausalLM": "modeling_xmodel.XModelForCausalLM"
  },
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5632,
  "max_position_embeddings": 131072,
  "model_type": "xmodel",
  "num_attention_heads": 32,
  "num_hidden_layers": 24,
  "num_key_value_heads": 4,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.37.2",
  "use_cache": true,
  "vocab_size": 65280
}