GLM-4.5-AWQ / config.json
JunHowie's picture
Upload folder using huggingface_hub
b6ab461 verified
{
"name_or_path": "tclf90/GLM-4.5-AWQ",
"architectures": [
"Glm4MoeForCausalLM"
],
"attention_bias": true,
"attention_dropout": 0.0,
"pad_token_id": 151329,
"eos_token_id": [
151329,
151336,
151338
],
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"partial_rotary_factor": 0.5,
"initializer_range": 0.02,
"intermediate_size": 12288,
"max_position_embeddings": 131072,
"model_type": "glm4_moe",
"moe_intermediate_size": 1536,
"norm_topk_prob": true,
"num_attention_heads": 96,
"n_group": 1,
"topk_group": 1,
"n_routed_experts": 160,
"n_shared_experts": 1,
"routed_scaling_factor": 2.5,
"num_experts_per_tok": 8,
"first_k_dense_replace": 3,
"num_hidden_layers": 92,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 1000000,
"num_nextn_predict_layers": 1,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.54.0",
"use_cache": true,
"use_qk_norm": true,
"vocab_size": 151552,
"quantization_config": {
"quant_method": "awq_marlin",
"bits": 4,
"group_size": 128,
"version": "gemm",
"zero_point": true,
"modules_to_not_convert": ["model.embed_tokens", "model.layers.3.mlp.shared_experts.", "model.layers.4.mlp.shared_experts.", "model.layers.5.mlp.shared_experts.", "model.layers.6.mlp.shared_experts.", "model.layers.7.mlp.shared_experts.", "model.layers.8.mlp.shared_experts.", "model.layers.9.mlp.shared_experts.", "model.layers.10.mlp.shared_experts.", "model.layers.11.mlp.shared_experts.", "model.layers.12.mlp.shared_experts.", "model.layers.13.mlp.shared_experts.", "model.layers.14.mlp.shared_experts.", "model.layers.15.mlp.shared_experts.", "model.layers.16.mlp.shared_experts.", "model.layers.17.mlp.shared_experts.", "model.layers.18.mlp.shared_experts.", "model.layers.19.mlp.shared_experts.", "model.layers.20.mlp.shared_experts.", "model.layers.21.mlp.shared_experts.", "model.layers.22.mlp.shared_experts.", "model.layers.23.mlp.shared_experts.", "model.layers.24.mlp.shared_experts.", "model.layers.25.mlp.shared_experts.", "model.layers.26.mlp.shared_experts.", "model.layers.27.mlp.shared_experts.", "model.layers.28.mlp.shared_experts.", "model.layers.29.mlp.shared_experts.", "model.layers.30.mlp.shared_experts.", "model.layers.31.mlp.shared_experts.", "model.layers.32.mlp.shared_experts.", "model.layers.33.mlp.shared_experts.", "model.layers.34.mlp.shared_experts.", "model.layers.35.mlp.shared_experts.", "model.layers.36.mlp.shared_experts.", "model.layers.37.mlp.shared_experts.", "model.layers.38.mlp.shared_experts.", "model.layers.39.mlp.shared_experts.", "model.layers.40.mlp.shared_experts.", "model.layers.41.mlp.shared_experts.", "model.layers.42.mlp.shared_experts.", "model.layers.43.mlp.shared_experts.", "model.layers.44.mlp.shared_experts.", "model.layers.45.mlp.shared_experts.", "model.layers.46.mlp.shared_experts.", "model.layers.47.mlp.shared_experts.", "model.layers.48.mlp.shared_experts.", "model.layers.49.mlp.shared_experts.", "model.layers.50.mlp.shared_experts.", "model.layers.51.mlp.shared_experts.", "model.layers.52.mlp.shared_experts.", "model.layers.53.mlp.shared_experts.", "model.layers.54.mlp.shared_experts.", "model.layers.55.mlp.shared_experts.", "model.layers.56.mlp.shared_experts.", "model.layers.57.mlp.shared_experts.", "model.layers.58.mlp.shared_experts.", "model.layers.59.mlp.shared_experts.", "model.layers.60.mlp.shared_experts.", "model.layers.61.mlp.shared_experts.", "model.layers.62.mlp.shared_experts.", "model.layers.63.mlp.shared_experts.", "model.layers.64.mlp.shared_experts.", "model.layers.65.mlp.shared_experts.", "model.layers.66.mlp.shared_experts.", "model.layers.67.mlp.shared_experts.", "model.layers.68.mlp.shared_experts.", "model.layers.69.mlp.shared_experts.", "model.layers.70.mlp.shared_experts.", "model.layers.71.mlp.shared_experts.", "model.layers.72.mlp.shared_experts.", "model.layers.73.mlp.shared_experts.", "model.layers.74.mlp.shared_experts.", "model.layers.75.mlp.shared_experts.", "model.layers.76.mlp.shared_experts.", "model.layers.77.mlp.shared_experts.", "model.layers.78.mlp.shared_experts.", "model.layers.79.mlp.shared_experts.", "model.layers.80.mlp.shared_experts.", "model.layers.81.mlp.shared_experts.", "model.layers.82.mlp.shared_experts.", "model.layers.83.mlp.shared_experts.", "model.layers.84.mlp.shared_experts.", "model.layers.85.mlp.shared_experts.", "model.layers.86.mlp.shared_experts.", "model.layers.87.mlp.shared_experts.", "model.layers.88.mlp.shared_experts.", "model.layers.89.mlp.shared_experts.", "model.layers.90.mlp.shared_experts.", "model.layers.91.mlp.shared_experts.", "model.layers.92.mlp.shared_experts.", "model.layers.92.shared_head.", "lm_head"]
}
}