config.json

{
  "architectures": [
    "TridaForDLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_trida.TridaConfig",
    "AutoModel": "modeling_trida.TridaForDLM",
    "AutoModelForCausalLM": "modeling_trida.TridaForDLM"
  },
  "bd_size": 32,
  "bos_token_id": 0,
  "dtype": "float32",
  "eos_token_id": 128001,
  "fuse_cross_entropy": false,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 4096,
  "max_window_layers": 28,
  "model_type": "Trida",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 100000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.1",
  "use_cache": false,
  "use_sliding_window": false,
  "vocab_size": 128256
}