GLM-4.5V-AWQ / config.json
tclf90's picture
Update config.json
57b42d7 verified
{
"name_or_path": "tclf90/GLM-4.5V-AWQ",
"architectures": [
"Glm4vMoeForConditionalGeneration"
],
"model_type": "glm4v_moe",
"text_config": {
"pad_token_id": 151329,
"vocab_size": 151552,
"eos_token_id": [
151329,
151336,
151338
],
"image_end_token_id": 151340,
"image_start_token_id": 151339,
"image_token_id": 151363,
"head_dim": 128,
"attention_bias": true,
"attention_dropout": 0.0,
"first_k_dense_replace": 1,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11264,
"max_position_embeddings": 65536,
"model_type": "glm4v_moe_text",
"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,
"partial_rotary_factor": 0.5,
"rms_norm_eps": 1e-05,
"torch_dtype": "bfloat16",
"rope_scaling": {
"rope_type": "default",
"mrope_section": [
8,
12,
12
]
},
"rope_theta": 10000.0,
"routed_scaling_factor": 1.0,
"topk_group": 1,
"use_cache": true,
"use_qk_norm": false
},
"torch_dtype": "float16",
"transformers_version": "4.55.0.dev0",
"video_end_token_id": 151342,
"video_start_token_id": 151341,
"video_token_id": 151364,
"vision_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"depth": 24,
"hidden_act": "silu",
"hidden_size": 1536,
"image_size": 336,
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 11264,
"model_type": "glm4v_moe",
"num_heads": 12,
"out_hidden_size": 4096,
"patch_size": 14,
"rms_norm_eps": 1e-05,
"spatial_merge_size": 2,
"temporal_patch_size": 2
},
"quantization_config": {
"quant_method": "awq_marlin",
"bits": 4,
"group_size": 128,
"version": "gemm",
"zero_point": true,
"modules_to_not_convert": ["visual.", "model.embed_tokens", "model.layers.0.mlp.shared_experts.", "model.layers.1.mlp.shared_experts.", "model.layers.2.mlp.shared_experts.", "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.", "lm_head"]
}
}