MGM-7B-HD / config.json
YanweiLi's picture
update config
5de77a5
{
"_name_or_path": "model_zoo/LLM/vicuna/7B-V1.5",
"architectures": [
"MiniGeminiLlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"aux_img_fold": false,
"aux_with_fpn": false,
"bos_token_id": 1,
"eos_token_id": 2,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 4096,
"image_aspect_ratio": "pad",
"image_global": true,
"image_grid": 2,
"image_grid_pinpoints": null,
"image_size_aux": 1536,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"mm_hidden_size": 1024,
"mm_hidden_size_aux": 2880,
"mm_projector_lr": null,
"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/OpenAI/clip-vit-large-patch14-336",
"mm_vision_tower_aux": "model_zoo/OpenAI/openclip-convnext-large-d-320-laion2B-s29B-b131K-ft-soup",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"optimize_vision_tower": false,
"optimize_vision_tower_aux": false,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"tokenizer_model_max_length": 4096,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.36.2",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mm_proj": true,
"video_grid": -1,
"vocab_size": 32000
}