internvl_ola / config.json
jjw0126's picture
Upload files
62d115a verified
{
"architectures": [
"InternVLChatModel"
],
"auto_map": {
"AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
"AutoModel": "modeling_internvl_chat.InternVLChatModel",
"AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
},
"downsample_ratio": 0.5,
"dynamic_image_size": true,
"eos_token_id": 151645,
"force_image_size": 448,
"llm_config": {
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"debug": false,
"eos_token_id": 151645,
"ep_size": 1,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"max_position_embeddings": 40960,
"max_window_layers": 28,
"micro_forward": false,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"skip_checkpoint": false,
"sliding_window": null,
"torch_dtype": "bfloat16",
"use_cache": false,
"use_deepep": false,
"use_sliding_window": false,
"vocab_size": 151936
},
"max_dynamic_patch": 12,
"min_dynamic_patch": 1,
"model_type": "internvl_chat",
"pad2square": false,
"pad_token_id": 151643,
"ps_version": "v2",
"select_layer": -1,
"template": "plm_v",
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": null,
"use_backbone_lora": 0,
"use_llm_lora": 0,
"use_thumbnail": true,
"vision_config": {
"architectures": [
"InternVisionModel"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_intern_vit.InternVisionConfig",
"AutoModel": "modeling_intern_vit.InternVisionModel"
},
"drop_path_rate": 0.0,
"dropout": 0.0,
"hidden_act": "gelu",
"hidden_size": 1024,
"image_size": 448,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-06,
"model_type": "intern_vit_6b",
"norm_type": "layer_norm",
"num_attention_heads": 16,
"num_channels": 3,
"num_hidden_layers": 24,
"patch_size": 14,
"qk_normalization": false,
"qkv_bias": true,
"torch_dtype": "bfloat16",
"use_fa3": false,
"use_flash_attn": true
},
"audio_config": {
"architectures": [
"DualWrappedEncoder"
],
"model_type": "whisper_beats",
"speech_encoder": "large-v3",
"speech_encoder_type": "whisper",
"speech_projector_type": "linear",
"speech_encoder_ds_rate": 5,
"speech_encoder_hidden_size": 1280,
"mel_bins": 80,
"sample_rate": 16000,
"frame_length": 25,
"frame_shift": 10,
"torch_dtype": "bfloat16",
"use_beats": true,
"beats_model_path": "./BEATs_iter3_plus_AS2M_finetuned_on_AS2M_cpt2.pt",
"speech_projector": null,
"whisper_config": {
"vocab_size": 51865,
"num_mel_bins": 80,
"encoder_layers": 6,
"encoder_attention_heads": 8,
"decoder_layers": 6,
"decoder_attention_heads": 8,
"decoder_ffn_dim": 1536,
"encoder_ffn_dim": 1536,
"encoder_layerdrop": 0.0,
"decoder_layerdrop": 0.0,
"decoder_start_token_id": 50257,
"use_cache": true,
"is_encoder_decoder": true,
"activation_function": "gelu",
"d_model": 512,
"dropout": 0.0,
"attention_dropout": 0.0,
"activation_dropout": 0.0,
"init_std": 0.02,
"scale_embedding": false,
"max_source_positions": 1500,
"max_target_positions": 448,
"pad_token_id": 50256,
"bos_token_id": 50257,
"eos_token_id": 50256,
"suppress_tokens": [1, 2, 7, 8, 9, 10, 14, 25, 26, 27, 28, 29, 31, 58, 59, 60, 61, 62, 63, 90, 91, 92, 93, 359, 503, 522, 542, 873, 893, 902, 918, 922, 931, 1350, 1853, 1982, 2460, 2627, 3246, 3253, 3268, 3536, 3846, 3961, 4183, 4667, 6585, 6647, 7273, 9061, 9383, 10428, 10929, 11938, 12033, 12331, 12562, 13793, 14157, 14635, 15265, 15618, 16553, 16604, 18362, 18956, 20075, 21675, 22520, 26130, 26161, 26435, 28279, 29464, 31650, 32302, 32470, 36865, 42863, 47425, 49870, 50254, 50258, 50358, 50359, 50360, 50361, 50362],
"begin_suppress_tokens": [220, 50256]
}
}
}