config.json

{
  "architectures": [
    "Cohere2MoeForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 2,
  "dtype": "bfloat16",
  "eos_token_id": 255001,
  "expert_selection_fn": "sigmoid",
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 768,
  "layer_norm_eps": 1e-05,
  "layer_types": [
    "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",
    "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": 500000,
  "mlp_layer_types": [
    "dense",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse"
  ],
  "model_type": "cohere2_moe",
  "norm_topk_prob": false,
  "num_attention_heads": 32,
  "num_experts": 128,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 49,
  "num_key_value_heads": 4,
  "num_shared_experts": 0,
  "pad_token_id": 0,
  "prefix_dense_intermediate_size": 3072,
  "prefix_dense_sliding_window_pattern": 1,
  "quantization_config": {
    "autoround_version": "0.13.1",
    "bits": 4,
    "block_name_to_quantize": "model.layers",
    "data_type": "int",
    "extra_config": {
      ".*model\\.layers\\.[1-48]\\.mlp\\.gate.*": {
        "bits": 16,
        "data_type": "float"
      }
    },
    "group_size": 128,
    "low_gpu_mem_usage": true,
    "packing_format": "auto_round:auto_gptq",
    "quant_method": "auto-round",
    "sym": true
  },
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "rope_theta": 50000,
    "rope_type": "default"
  },
  "rope_scaling": null,
  "rope_theta": 50000,
  "shared_expert_combination_strategy": "average",
  "sliding_window": 4096,
  "sliding_window_pattern": 4,
  "tie_word_embeddings": true,
  "transformers_version": "5.12.0",
  "use_cache": true,
  "use_gated_activation": true,
  "use_parallel_block": true,
  "use_parallel_embedding": false,
  "use_qk_norm": false,
  "vocab_size": 262144
}