config.json

{
  "_sliding_window_pattern": 4,
  "architectures": [
    "Cohere2ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 5,
  "dtype": "bfloat16",
  "eos_token_id": 255001,
  "head_dim": 2,
  "hidden_act": "silu",
  "hidden_size": 8,
  "initializer_range": 0.02,
  "intermediate_size": 32,
  "layer_norm_eps": 1e-05,
  "layer_types": [
    "sliding_attention",
    "sliding_attention"
  ],
  "logit_scale": 0.0625,
  "max_position_embeddings": 8192,
  "model_type": "cohere2",
  "num_attention_heads": 4,
  "num_hidden_layers": 2,
  "num_key_value_heads": 2,
  "pad_token_id": 0,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "sliding_window": 4096,
  "tie_word_embeddings": true,
  "transformers_version": "5.2.0.dev0",
  "use_cache": true,
  "vocab_size": 261010
}