add readme (#10)

* Update Readme.md

* Update Readme.md

* Update Readme.md

* Update Readme.md

* Update Readme.md

* Update Readme.md

* Update Readme.md

* Update Readme.md

* Update Readme.md

* Update Readme.md

* Update Readme.md

* Update Readme.md

* Update Readme.md

* remove submodule

* add mPLUG MiniGPT4

* Update Readme.md

* Update Readme.md

* Update Readme.md

---------

Co-authored-by: Yuliang Liu <34134635+Yuliang-Liu@users.noreply.github.com>

models/MiniGPT4/train_configs/minigpt4_stage1_pretrain.yaml

@@ -0,0 +1,57 @@
+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

models/MiniGPT4/train_configs/minigpt4_stage2_finetune.yaml

@@ -0,0 +1,51 @@
+model:
+  arch: mini_gpt4
+  model_type: pretrain_vicuna
+  freeze_vit: True
+  freeze_qformer: True
+  max_txt_len: 160
+  end_sym: "###"
+  prompt_path: "prompts/alignment.txt"
+  prompt_template: '###Human: {} ###Assistant: '
+  ckpt: '/path/to/stage1/checkpoint/'
+
+
+datasets:
+  cc_sbu_align:
+    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
+  batch_size_train: 12
+  batch_size_eval: 12
+  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