config.json

{
  "architectures": [
    "TransnormerForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_transnormer.TransnormerConfig",
    "AutoModelForCausalLM": "modeling_transnormer.TransnormerForCausalLM"
  },
  "pad_token_id": 0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "vocab_size": 64000,
  "use_cache": true,
  "init_std": 0.02,
  "decoder_embed_dim": 4096,
  "decoder_layers": 30,
  "decoder_attention_heads": 32,
  "no_scale_embedding": true,
  "add_bos_token": false,
  "norm_type": "simplermsnorm",
  "linear_use_lrpe_list": [
    1,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0
  ],
  "hidden_dim": 4096,
  "linear_act_fun": "swish",
  "glu_dim": 11008,
  "bias": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.32.0"
}