Image-Text-to-Text
Safetensors
llava_llama
UGround / config.json
BoyuNLP's picture
Upload config.json with huggingface_hub
7bea2a9 verified
{
"_name_or_path": "/fs/ess/PAS1576/boyu_gou/train_vlm/ui_llava_fine_tune/checkpoints/base/merged_llava-v1.5-vicuna-7b-16k-pad-no-fusion_converted/",
"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": "anyres_ui",
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"max_sequence_length": 16384,
"mm_hidden_size": 1024,
"mm_patch_merge_type": "spatial",
"mm_projector_lr": 2e-05,
"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": "openai/clip-vit-large-patch14",
"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": {
"factor": 4.0,
"type": "linear"
},
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"tokenizer_model_max_length": 16384,
"tokenizer_padding_side": "right",
"torch_dtype": "float16",
"transformers_version": "4.37.2",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mm_proj": true,
"vocab_size": 32000
}