MixLoRA_E32_r4 / config.json
yingss's picture
init commit
6480168
{
"_name_or_path": "lmsys/vicuna-7b-v1.3",
"architectures": [
"LlamaForCausalLM"
],
"attribute_len": 6,
"bos_token_id": 1,
"cond_type": "input_lora_a_param",
"eos_token_id": 2,
"freeze_mm_mlp_adapter": false,
"grad_sim": false,
"hidden_act": "silu",
"hidden_size": 4096,
"image_aspect_ratio": "square",
"image_grid_pinpoints": null,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 2048,
"mix_mm_projector": false,
"mm_hidden_size": 1024,
"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": "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-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"task_model_name_or_path": "lmsys/vicuna-7b-v1.3",
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.33.3",
"tune_mm_mlp_adapter": false,
"use_cache": false,
"use_cmoa": true,
"use_contrastive_instr_token": false,
"use_mm_proj": true,
"vocab_size": 32000
}