config.json

{
  "allow_negative_eigenvalues": false,
  "architecture": "TinyGDNForCausalLM",
  "architectures": [
    "TinyGDNForCausalLM"
  ],
  "attention_dropout": 0.0,
  "attention_head_dim": 128,
  "base_model": "kerzgrr/Monostich-2-base",
  "bos_token_id": 0,
  "checkpoint_step": 10619,
  "eos_token_id": 1,
  "full_attention_interval": 4,
  "hidden_size": 512,
  "initializer_range": 0.02,
  "intermediate_size": 1472,
  "layer_types": [
    "gdn2",
    "gdn2",
    "gdn2",
    "full_attention",
    "gdn2",
    "gdn2",
    "gdn2",
    "full_attention",
    "gdn2",
    "gdn2",
    "gdn2",
    "full_attention",
    "gdn2",
    "gdn2",
    "gdn2",
    "full_attention",
    "gdn2",
    "gdn2",
    "gdn2",
    "full_attention",
    "gdn2",
    "gdn2",
    "gdn2",
    "full_attention",
    "gdn2",
    "gdn2",
    "gdn2",
    "full_attention",
    "gdn2",
    "gdn2",
    "gdn2",
    "full_attention"
  ],
  "linear_conv_kernel_dim": 4,
  "linear_expand_v": 1.0,
  "linear_head_dim": 128,
  "linear_num_heads": 4,
  "linear_num_value_heads": 4,
  "max_position_embeddings": 32768,
  "model_family": "Monostich-2",
  "model_name": "Monostich-2",
  "model_type": "tiny_gdn",
  "mtp_adapter_rank": 128,
  "mtp_loss_weight": 0.0,
  "mtp_num_heads": 0,
  "num_attention_heads": 4,
  "num_hidden_layers": 32,
  "num_key_value_heads": 1,
  "pad_token_id": 2,
  "partial_rotary_factor": 0.5,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sft_hours": 21.7,
  "sft_val_loss_ema": 1.5321617420986058,
  "sft_val_ppl_ema": 4.628170928002891,
  "shared_layer_indices": [],
  "stage": "sft",
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "training_sequence_length": 8192,
  "transformers_version": "4.45.0",
  "unk_token_id": 3,
  "vocab_size": 49152,
  "weights": "ema"
}