|
{ |
|
"X": [ |
|
"Video", |
|
"Image" |
|
], |
|
"_name_or_path": "/mnt/bn/liangkeg/ruohongz/save/gpt4v_video_alignment//Video-LLaVA-Finetune-frames-video-900k+image-650k-pretrain", |
|
"architectures": [ |
|
"LlavaLlamaForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 1, |
|
"eos_token_id": 2, |
|
"freeze_mm_mlp_adapter": false, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"image_aspect_ratio": "pad", |
|
"image_grid_pinpoints": null, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 11008, |
|
"max_position_embeddings": 4096, |
|
"mm_hidden_size": 1024, |
|
"mm_image_tower": "LanguageBind/LanguageBind_Image", |
|
"mm_projector_type": "mlp2x_gelu", |
|
"mm_use_x_patch_token": false, |
|
"mm_use_x_start_end": false, |
|
"mm_video_tower": "LanguageBind/LanguageBind_Video_merge", |
|
"mm_vision_select_feature": "patch", |
|
"mm_vision_select_layer": -2, |
|
"model_type": "llava_llama", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 32, |
|
"pad_token_id": 0, |
|
"pretraining_tp": 1, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"rope_theta": 10000.0, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.36.2", |
|
"tune_mm_mlp_adapter": false, |
|
"use_cache": true, |
|
"use_mm_proj": true, |
|
"vocab_size": 32000 |
|
} |
|
|