llava-mlan-llama2-7b / config.json
ToviTu's picture
Upload LlavaLlamaForCausalLM
56f267a verified
{
"_name_or_path": "/storage1/chenguangwang/Active/t.tovi/models/llava-llama2-7b-lit-flan",
"architectures": [
"LlavaLlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"freeze_backbone": false,
"freeze_mm_mlp_adapter": true,
"freeze_vision_tower": true,
"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": 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": "openai/clip-vit-large-patch14-336",
"model_type": "llava_llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"tokenizer_model_max_length": 2048,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.37.2",
"use_cache": true,
"use_mm_proj": true,
"vocab_size": 32000
}