config.json

{
  "architectures": [
    "Glm4MoeLiteForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "pad_token_id": 154820,
  "eos_token_id": [
    154820,
    154827,
    154829
  ],
  "hidden_act": "silu",
  "hidden_size": 2048,
  "intermediate_size": 10240,
  "max_position_embeddings": 202752,
  "model_type": "glm4_moe_lite",
  "moe_intermediate_size": 1536,
  "topk_method": "noaux_tc",
  "norm_topk_prob": true,
  "num_attention_heads": 20,
  "n_group": 1,
  "topk_group": 1,
  "n_routed_experts": 64,
  "n_shared_experts": 1,
  "routed_scaling_factor": 1.8,
  "num_experts_per_tok": 4,
  "first_k_dense_replace": 1,
  "num_hidden_layers": 47,
  "num_key_value_heads": 20,
  "num_nextn_predict_layers": 1,
  "partial_rotary_factor": 1.0,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "tie_word_embeddings": false,
  "dtype": "bfloat16",
  "transformers_version": "5.0.0rc0",
  "q_lora_rank": 768,
  "kv_lora_rank": 512,
  "qk_nope_head_dim": 192,
  "qk_rope_head_dim": 64,
  "v_head_dim": 256,
  "vocab_size": 154880,
  "quantization_config": {
    "quant_method": "compressed-tensors",
    "config_groups": {
      "group_0": {
        "input_activations": {
          "num_bits": 4,
          "type": "float",
          "strategy": "tensor_group",
          "group_size": 16,
          "symmetric": true,
          "dynamic": true
        },
        "weights": {
          "num_bits": 4,
          "type": "float",
          "strategy": "tensor_group",
          "group_size": 16,
          "symmetric": true
        },
        "targets": [
          "Linear"
        ]
      }
    },
    "format": "nvfp4-pack-quantized",
    "ignore": [
      "lm_head",
      "re:.*embed.*",
      "re:.*gate$",
      "re:.*self_attn.*"
    ],
    "dynamic": true
  }
}