config.json

{
  "architectures": [
    "SophiaForCausalLM"
  ],
  "attention_dropout": 0.0,
  "attn_res_block_size": 4,
  "auto_map": {
    "AutoConfig": "modeling_sophia.SophiaConfig",
    "AutoModelForCausalLM": "modeling_sophia.SophiaForCausalLM"
  },
  "bos_token_id": 2,
  "dim": 1536,
  "dropout": 0.0,
  "eos_token_id": 3,
  "ffn_hidden": 3968,
  "gradient_checkpointing_exclude_first": 0,
  "gradient_checkpointing_exclude_last": 0,
  "head_dim": 128,
  "hidden_size": 1536,
  "initializer_range": 0.02,
  "kda_a_log_init": 0.0,
  "kda_backend": "auto",
  "kda_decay_lower_bound": -5.0,
  "kda_decay_rank": 128,
  "kda_dt_floor": 0.0001,
  "kda_dt_max": 0.1,
  "kda_dt_min": 0.001,
  "kda_output_gate_full_rank": true,
  "kda_output_gate_rank": 128,
  "loss_chunk_size": 0,
  "max_batch_size": 1,
  "max_position_embeddings": 4096,
  "max_seq_len": 4096,
  "mla_kv_rank": 128,
  "mla_q_rank": 384,
  "model_type": "sophia_hybrid",
  "n_layers": 28,
  "norm_eps": 1e-05,
  "num_attention_heads": 16,
  "num_heads": 16,
  "num_hidden_layers": 28,
  "pad_token_id": 0,
  "return_logits_in_train": false,
  "rms_norm_eps": 1e-05,
  "short_conv_kernel": 4,
  "situ_gate_softcap": 4.0,
  "situ_up_softcap": 25.0,
  "sliding_window": 4096,
  "tie_word_embeddings": true,
  "transformers_version": "5.10.2",
  "unk_token_id": 1,
  "use_cache": true,
  "vocab_size": 65536
}