config.json

{
  "architectures": [
    "Cohere2MoeForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 2,
  "dtype": "float16",
  "eos_token_id": 255001,
  "expert_selection_fn": "sigmoid",
  "first_k_dense_replace": 1,
  "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": {
    "config_groups": {
      "group_0": {
        "format": "pack-quantized",
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 32,
          "num_bits": 4,
          "observer": "mse",
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "group",
          "symmetric": false,
          "type": "int",
          "zp_dtype": "torch.int8"
        }
      }
    },
    "format": "pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "model.layers.0.self_attn.q_proj",
      "model.layers.0.self_attn.k_proj",
      "model.layers.0.self_attn.v_proj",
      "model.layers.0.self_attn.o_proj",
      "model.layers.0.mlp.gate_proj",
      "model.layers.0.mlp.up_proj",
      "model.layers.0.mlp.down_proj",
      "lm_head",
      "re:.*mlp[.]gate"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.1.dev489+g6d69620"
  },
  "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": "5.10.2",
  "use_cache": true,
  "use_gated_activation": true,
  "use_parallel_block": true,
  "use_parallel_embedding": false,
  "use_qk_norm": false,
  "vocab_size": 262144
}