config.json

{
  "architectures": [
    "CwmForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "dtype": "float32",
  "eos_token_id": 128001,
  "head_dim": 16,
  "hidden_act": "gelu",
  "hidden_size": 32,
  "initializer_range": 0.02,
  "intermediate_size": 32,
  "is_decoder": true,
  "layer_types": [
    "full_attention",
    "sliding_attention"
  ],
  "max_position_embeddings": 512,
  "mlp_bias": false,
  "model_type": "cwm",
  "num_attention_heads": 2,
  "num_hidden_layers": 2,
  "num_key_value_heads": 2,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "factor": 16.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_theta": 1000000.0,
    "rope_type": "llama3"
  },
  "sliding_window": 8192,
  "tie_word_embeddings": false,
  "transformers_version": "5.16.0.dev0",
  "use_cache": true,
  "vocab_size": 128256
}