config.json

{
  "_sliding_window_pattern": 4,
  "architectures": [
    "Cohere2ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 2,
  "cache_implementation": "hybrid",
  "dtype": "bfloat16",
  "eos_token_id": 6,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "layer_norm_eps": 1e-05,
  "layer_switch": 4,
  "layer_types": [
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention"
  ],
  "logit_scale": 1.0,
  "max_position_embeddings": 512,
  "model_type": "cohere2",
  "num_attention_heads": 16,
  "num_hidden_layers": 36,
  "num_key_value_heads": 4,
  "order_of_interleaved_layers": "local_attn_first",
  "pad_token_id": 0,
  "position_embedding_type": "rope_gptj",
  "rope_parameters": {
    "rope_theta": 50000,
    "rope_type": "default"
  },
  "rotary_pct": 1.0,
  "sliding_window": 4096,
  "sliding_window_pattern": 4,
  "tie_word_embeddings": true,
  "transformers_version": "5.0.0",
  "use_cache": false,
  "use_embedding_sharing": true,
  "use_gated_activation": true,
  "use_parallel_block": true,
  "use_parallel_embedding": false,
  "use_qk_norm": false,
  "vocab_size": 262144
}