llama-vid-13b-full-336 / config.json
YanweiLi's picture
Upload 11 files
54e269f
{
"_name_or_path": "model_zoo/LLM/vicuna/13B-V1.5",
"architectures": [
"LlavaLlamaAttForCausalLM"
],
"bert_type": "qformer_pretrain",
"bos_token_id": 1,
"compress_type": null,
"eos_token_id": 2,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 5120,
"image_aspect_ratio": "pad",
"image_grid_pinpoints": null,
"image_processor": "./llamavid/processor/clip-patch14-336",
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_length": 4096,
"max_position_embeddings": 4096,
"max_token": 4096,
"mm_hidden_size": 1408,
"mm_projector_type": "mlp2x_gelu",
"mm_use_im_patch_token": false,
"mm_use_im_start_end": false,
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -2,
"mm_vision_tower": "./model_zoo/LAVIS/eva_vit_g.pth",
"model_type": "llava",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"num_query": 32,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.31.0",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mm_proj": true,
"vocab_size": 32000
}