Visual Question Answering
Transformers
Safetensors
English
videollama2_qwen2
text-generation
multimodal large language model
large video-language model
Inference Endpoints
VideoLLaMA2-72B / config.json
lixin4ever's picture
Update config.json
b6fb50e verified
{
"_name_or_path": "/mnt/workspace/zh/72b/VideoLLaMA2/work_dirs/videollama2qwen2/VideoLLaMA2-72B",
"architectures": [
"Videollama2Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 8192,
"image_aspect_ratio": "pad",
"initializer_range": 0.02,
"intermediate_size": 29568,
"max_position_embeddings": 32768,
"max_window_layers": 80,
"mm_hidden_size": 1024,
"mm_projector_lr": null,
"mm_projector_type": "stc_connector",
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -2,
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
"model_type": "videollama2_qwen2",
"num_attention_heads": 64,
"num_frames": 16,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"tokenizer_model_max_length": 2048,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.44.0",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mm_proj": true,
"use_sliding_window": false,
"vocab_size": 152064
}