mllava-baichuan2-en-zh / config.json
amitha's picture
Upload LlavaBaichuanForCausalLM
3b5a7e5 verified
{
"_from_model_config": true,
"_name_or_path": "baichuan-inc/Baichuan2-7B-Chat",
"architectures": [
"LlavaBaichuanForCausalLM"
],
"auto_map": {
"AutoConfig": "llava_baichuan.LlavaBaichuanConfig",
"AutoModelForCausalLM": "baichuan-inc/Baichuan2-7B-Chat--modeling_baichuan.BaichuanForCausalLM",
"AutoModelForVisualQuestionAnswering": "llava_baichuan.LlavaBaichuanForCausalLM"
},
"bos_token_id": 1,
"eos_token_id": 2,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 4096,
"image_aspect_ratio": "pad",
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"mm_hidden_size": 1024,
"mm_patch_merge_type": "flat",
"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-patch14-336",
"model_max_length": 4096,
"model_type": "llava_baichuan",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"tokenizer_class": "BaichuanTokenizer",
"tokenizer_model_max_length": 2048,
"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": 125696,
"z_loss_weight": 0
}