VideoLLaMA2.1-7B-AV / config.json
阔毅
add VideoLLaMA2.1-AV model
acd1625
{
"_name_or_path": "DAMO-NLP-SG/VideoLLaMA2.1-7B-16F",
"architectures": [
"Videollama2Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 3584,
"hidden_size_a": 3584,
"image_aspect_ratio": "pad",
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 32768,
"max_window_layers": 28,
"mm_audio_tower": "work_dirs/VideoLLaMA2.1-7B-A/audio_tower.bin",
"mm_hidden_size": 1152,
"mm_hidden_size_a": 768,
"mm_projector_a_type": "mlp2x_gelu",
"mm_projector_lr": null,
"mm_projector_type": "stc_connector_v35",
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -2,
"mm_vision_tower": "google/siglip-so400m-patch14-384",
"model_type": "videollama2_qwen2",
"num_attention_heads": 28,
"num_frames": 8,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": false,
"tokenizer_model_max_length": 2048,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.42.3",
"tune_mm_mlp_adapter": false,
"tune_mm_mlp_adapter_a": true,
"use_cache": true,
"use_mm_proj": true,
"use_sliding_window": false,
"vocab_size": 152064
}