Spaces:
Running
Running
File size: 1,343 Bytes
dc80a97 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 |
model:
arch: mini_gpt4_llama_v2
model_type: minigpt4_video
llama_model: "meta-llama/Llama-2-7b-chat-hf"
max_txt_len: 160
max_context_len: 512
end_sym: "</s>"
prompt_path: "train_configs/alignment.txt"
prompt_template: '[INST] {} [/INST] '
ckpt: put your pretrained ckpt here
architectures: [
"MiniGPT4_Video"
]
device: "cuda"
drop_path_rate: 0
img_size: 224
model_type: "minigpt4_video"
num_query_token: 32
prompt: ""
torch_dtype: "float32"
vit_precision: "fp16"
vit_model: "eva_clip_g"
lora_target_modules : ["q_proj","v_proj"]
lora_dropout: 0.05
remove_template: false
token_pooling: True
datasets:
cc_sbu_align:
batch_size: 12
vis_processor:
train:
name: "blip2_image_train"
image_size: 224
text_processor:
train:
name: "blip_caption"
run:
task: image_text_pretrain
# optimizer
lr_sched: "linear_warmup_cosine_lr"
init_lr: 3e-5
min_lr: 1e-5
warmup_lr: 1e-6
weight_decay: 0.05
max_epoch: 5
iters_per_epoch: 200
num_workers: 4
warmup_steps: 200
seed: 42
output_dir: "output/minigpt4_stage2_finetune"
amp: True
resume_ckpt_path: null
evaluate: False
train_splits: ["train"]
device: "cuda"
world_size: 1
dist_url: "env://"
distributed: True
wandb_log: True
job_name: minigpt4_finetune
|