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/minigpt4/configs/datasets/cc_sbu/align.yaml

@@ -0,0 +1,5 @@
+datasets:
+  cc_sbu_align:
+    data_type: images
+    build_info:
+      storage: /path/to/cc_sbu_align/

models/MiniGPT4/minigpt4/configs/datasets/cc_sbu/defaults.yaml

@@ -0,0 +1,5 @@
+datasets:
+  cc_sbu:
+    data_type: images
+    build_info:
+      storage: /path/to/cc_sbu_dataset/{00000..01255}.tar

models/MiniGPT4/minigpt4/configs/datasets/laion/defaults.yaml

@@ -0,0 +1,5 @@
+datasets:
+  laion:
+    data_type: images
+    build_info:
+      storage: /path/to/laion_dataset/{00000..10488}.tar

models/MiniGPT4/minigpt4/configs/default.yaml

@@ -0,0 +1,5 @@
+env:
+  # For default users
+  # cache_root: "cache"
+  # For internal use with persistent storage
+  cache_root: "/export/home/.cache/minigpt4"

models/MiniGPT4/minigpt4/configs/models/minigpt4.yaml

@@ -0,0 +1,33 @@
+model:
+  arch: mini_gpt4
+
+  # vit encoder
+  image_size: 224
+  drop_path_rate: 0
+  use_grad_checkpoint: False
+  vit_precision: "fp16"
+  freeze_vit: True
+  freeze_qformer: True
+
+  # Q-Former
+  num_query_token: 32
+
+  # Vicuna
+  llama_model: "./models/MiniGPT4/model_weight/model"
+
+  # generation configs
+  prompt: ""
+
+preprocess:
+    vis_processor:
+        train:
+          name: "blip2_image_train"
+          image_size: 224
+        eval:
+          name: "blip2_image_eval"
+          image_size: 224
+    text_processor:
+        train:
+          name: "blip_caption"
+        eval:
+          name: "blip_caption"