step_000000000555/config.json

{
  "architectures": [
    "ItttModel"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "base_lr": 0.001,
  "base_model": "HuggingFaceTB/SmolLM2-360M-Instruct",
  "bos_token_id": 1,
  "disable_fast_weights": false,
  "dtype": "float32",
  "eos_token_id": 2,
  "fast_weight_size": 640,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 960,
  "initializer_range": 0.02,
  "intermediate_size": 2560,
  "is_llama_config": true,
  "max_position_embeddings": 8192,
  "mlp_bias": false,
  "model_type": "ittt",
  "momentum_beta": 0.9,
  "momentum_dtype": "bfloat16",
  "num_attention_heads": 15,
  "num_hidden_layers": 32,
  "num_key_value_heads": 5,
  "pad_token_id": 2,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_interleaved": false,
  "rope_scaling": null,
  "rope_theta": 100000,
  "state_dtype": "float32",
  "transformers.js_config": {
    "kv_cache_dtype": {
      "fp16": "float16",
      "q4f16": "float16"
    }
  },
  "transformers_version": "4.57.3",
  "use_cache": true,
  "vocab_size": 49152
}