config.json

{
    "architectures": [
        "Glm4MoeLiteForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "eos_token_id": [
        154820,
        154827,
        154829
    ],
    "first_k_dense_replace": 1,
    "head_dim": 64,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 10240,
    "kv_lora_rank": 512,
    "max_position_embeddings": 202752,
    "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"
    ],
    "model_type": "glm4_moe_lite",
    "moe_intermediate_size": 1536,
    "n_group": 1,
    "n_routed_experts": 64,
    "n_shared_experts": 1,
    "norm_topk_prob": true,
    "num_attention_heads": 20,
    "num_experts_per_tok": 4,
    "num_hidden_layers": 47,
    "num_key_value_heads": 20,
    "num_nextn_predict_layers": 1,
    "pad_token_id": 154821,
    "partial_rotary_factor": 1.0,
    "pretraining_tp": 1,
    "q_lora_rank": 768,
    "qk_head_dim": 256,
    "qk_nope_head_dim": 192,
    "qk_rope_head_dim": 64,
    "quantization": {
        "group_size": 64,
        "bits": 4,
        "mode": "affine"
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 4,
        "mode": "affine"
    },
    "rms_norm_eps": 1e-05,
    "rope_interleave": true,
    "rope_parameters": {
        "partial_rotary_factor": 1.0,
        "rope_theta": 1000000,
        "rope_type": "default"
    },
    "routed_scaling_factor": 1.8,
    "scoring_func": "sigmoid",
    "tie_word_embeddings": false,
    "topk_group": 1,
    "topk_method": "noaux_tc",
    "torch_dtype": "bfloat16",
    "transformers_version": "5.2.0.dev0",
    "unsloth_fixed": true,
    "use_cache": true,
    "v_head_dim": 256,
    "vocab_size": 154880
}