config.json

{
  "architectures": [
    "Glm4MoeForCausalLM"
  ],
  "attention_bias": true,
  "attention_dropout": 0.0,
  "eos_token_id": [
    151329,
    151336,
    151338
  ],
  "first_k_dense_replace": 1,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 10944,
  "max_position_embeddings": 131072,
  "model_type": "glm4_moe",
  "moe_intermediate_size": 1408,
  "n_group": 1,
  "n_routed_experts": 128,
  "n_shared_experts": 1,
  "norm_topk_prob": true,
  "num_attention_heads": 96,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 46,
  "num_key_value_heads": 8,
  "num_nextn_predict_layers": 1,
  "pad_token_id": 151329,
  "partial_rotary_factor": 0.5,
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 32,
          "num_bits": 4,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "group",
          "symmetric": true,
          "type": "int"
        }
      }
    },
    "format": "pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed"
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "routed_scaling_factor": 1.0,
  "tie_word_embeddings": false,
  "topk_group": 1,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.54.0",
  "use_cache": true,
  "use_qk_norm": false,
  "vocab_size": 151552
}