Hugging Face's logo

Spaces:
Vision-CAIR
/
MiniGPT-v2
Running on A10G

App Files Community
9
MiniGPT-v2
File size: 983 Bytes 
b98ba2b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
model:
  arch: mini_gpt4
  model_type: pretrain_vicuna
  freeze_vit: True
  freeze_qformer: True


datasets:
  laion:
    vis_processor:
      train:
        name: "blip2_image_train"
        image_size: 224
    text_processor:
      train:
        name: "blip_caption"
    sample_ratio: 115
  cc_sbu:
    vis_processor:
        train:
          name: "blip2_image_train"
          image_size: 224
    text_processor:
        train:
          name: "blip_caption"
    sample_ratio: 14


run:
  task: image_text_pretrain
  # optimizer
  lr_sched: "linear_warmup_cosine_lr"
  init_lr: 1e-4
  min_lr: 8e-5
  warmup_lr: 1e-6

  weight_decay: 0.05
  max_epoch: 4
  batch_size_train: 64
  batch_size_eval: 64
  num_workers: 4
  warmup_steps: 5000
  iters_per_epoch: 5000

  seed: 42
  output_dir: "output/minigpt4_stage1_pretrain"

  amp: True
  resume_ckpt_path: null

  evaluate: False 
  train_splits: ["train"]

  device: "cuda"
  world_size: 1
  dist_url: "env://"
  distributed: True