Xmodel_VLM / config.json
XiaoduoAILab's picture
Upload 2 files
3d3d450 verified
raw
history blame
1.27 kB
{
"_name_or_path": "/data1/liuyang/checkpoints/e_line/xl/iter-0504000/",
"architectures": [
"XmodelLMForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_xmodel.XModelConfig",
"AutoModelForCausalLM": "modeling_xmodel.XModelForCausalLM"
},
"bos_token_id": 1,
"eos_token_id": 2,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 2048,
"image_aspect_ratio": "pad",
"image_grid_pinpoints": null,
"initializer_range": 0.02,
"intermediate_size": 5632,
"max_position_embeddings": 32768,
"mm_hidden_size": 1024,
"mm_projector_lr": null,
"mm_projector_type": "xdpnetv10_4",
"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": "/data1/xuwanting/LLaVA/llava/model/clip-vit-large-patch14-336/",
"model_type": "xmodelvlm",
"num_attention_heads": 32,
"num_hidden_layers": 24,
"num_key_value_heads": 4,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.37.2",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mm_proj": true,
"vision_tower_type": "clip",
"vocab_size": 32000
}