EXAONE-4.5-33B / config.json
LG-AI-EXAONE's picture
Initial commit
acb250c
{
"architectures": [
"Exaone4_5_ForConditionalGeneration"
],
"image_token_id": 67,
"model_type": "exaone4_5",
"text_config": {
"_num_mtp_layers": 1,
"architectures": [
"Exaone4ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "bfloat16",
"eos_token_id": 53,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 27392,
"layer_types": [
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention"
],
"max_position_embeddings": 262144,
"num_nextn_predict_layers": 1,
"mtp_loss_scaling_factor": 0.05,
"mtp_share_layers": true,
"model_type": "exaone4_5_text",
"num_attention_heads": 40,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"pad_token_id": 0,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 16.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 1000000.0,
"sliding_window": 4096,
"sliding_window_pattern": "LLLG",
"tie_word_embeddings": false,
"use_cache": true,
"vocab_size": 153600
},
"transformers_version": "5.3.0.dev0",
"video_token_id": 68,
"vision_config": {
"depth": 28,
"dtype": "bfloat16",
"fullatt_block_indexes": [
6,
13,
20,
27
],
"hidden_act": "silu",
"hidden_size": 2048,
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 5120,
"model_type": "exaone4_5_vision",
"num_heads": 32,
"num_key_value_heads": 8,
"out_hidden_size": 5120,
"patch_size": 14,
"spatial_merge_size": 2,
"temporal_patch_size": 2,
"tokens_per_second": 2,
"window_size": 112
},
"vision_end_token_id": 74,
"vision_start_token_id": 73,
"vision_token_id": 67,
"vocab_size": 153600
}