GLM-4.6V / config.json
ZHANGYUXUAN-zR's picture
Update config.json
e5323a8 verified
raw
history blame
1.99 kB
{
"architectures": [
"Glm4vMoeForConditionalGeneration"
],
"model_type": "glm4v_moe",
"text_config": {
"attention_bias": true,
"attention_dropout": 0.0,
"dtype": "bfloat16",
"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": "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,
"num_nextn_predict_layers": 0,
"pad_token_id": 151329,
"partial_rotary_factor": 0.5,
"qk_layernorm": false,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"mrope_section": [
8,
12,
12
],
"partial_rotary_factor": 0.5,
"rope_theta": 500000,
"rope_type": "default"
},
"routed_scaling_factor": 1.0,
"topk_group": 1,
"use_cache": true,
"use_qk_norm": false,
"vocab_size": 151552
},
"tie_word_embeddings": false,
"transformers_version": "5.0.0rc0",
"image_start_token_id": 151339,
"image_end_token_id": 151340,
"video_start_token_id": 151341,
"video_end_token_id": 151342,
"image_token_id": 151363,
"video_token_id": 151364,
"vision_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"depth": 24,
"hidden_act": "silu",
"hidden_dropout_prob": 0.0,
"hidden_size": 1536,
"image_size": 336,
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 10944,
"model_type": "glm4v_moe_vision",
"num_heads": 12,
"out_hidden_size": 4096,
"patch_size": 14,
"rms_norm_eps": 1e-05,
"spatial_merge_size": 2,
"temporal_patch_size": 2
}
}