Support for bitsandbytes 0.39.1 with Paged Optimizer(AdamW8bit and Lion8bit) (#631)

* ADD libbitsandbytes.dll for 0.38.1

* Delete libbitsandbytes_cuda116.dll

* Delete cextension.py

* add main.py

* Update requirements.txt for bitsandbytes 0.38.1

* Update README.md for bitsandbytes-windows

* Update README-ja.md  for bitsandbytes 0.38.1

* Update main.py for return cuda118

* Update train_util.py for lion8bit

* Update train_README-ja.md for lion8bit

* Update train_util.py for add DAdaptAdan and DAdaptSGD

* Update train_util.py for DAdaptadam

* Update train_network.py for dadapt

* Update train_README-ja.md for DAdapt

* Update train_util.py for DAdapt

* Update train_network.py for DAdaptAdaGrad

* Update train_db.py for DAdapt

* Update fine_tune.py for DAdapt

* Update train_textual_inversion.py for DAdapt

* Update train_textual_inversion_XTI.py for DAdapt

* Revert "Merge branch 'qinglong' into main"

This reverts commit b65c023083, reversing
changes made to f6fda20caf.

* Revert "Update requirements.txt for bitsandbytes 0.38.1"

This reverts commit 83abc60dfa.

* Revert "Delete cextension.py"

This reverts commit 3ba4dfe046.

* Revert "Update README.md for bitsandbytes-windows"

This reverts commit 4642c52086.

* Revert "Update README-ja.md  for bitsandbytes 0.38.1"

This reverts commit fa6d7485ac.

* Update train_util.py

* Update requirements.txt

* support PagedAdamW8bit/PagedLion8bit

* Update requirements.txt

* update for PageAdamW8bit and PagedLion8bit

* Revert

* revert main

library/train_util.py

@@ -2033,7 +2033,7 @@ def add_optimizer_arguments(parser: argparse.ArgumentParser):
         "--optimizer_type",
         type=str,
         default="",
-        help="Optimizer to use / オプティマイザの種類: AdamW (default), AdamW8bit, Lion8bit, Lion, SGDNesterov, SGDNesterov8bit, DAdaptation(DAdaptAdamPreprint), DAdaptAdaGrad, DAdaptAdam, DAdaptAdan, DAdaptAdanIP, DAdaptLion, DAdaptSGD, AdaFactor",
+        help="Optimizer to use / オプティマイザの種類: AdamW (default), AdamW8bit, PagedAdamW8bit, Lion8bit, PagedLion8bit, Lion, SGDNesterov, SGDNesterov8bit, DAdaptation(DAdaptAdamPreprint), DAdaptAdaGrad, DAdaptAdam, DAdaptAdan, DAdaptAdanIP, DAdaptLion, DAdaptSGD, AdaFactor",
     )
 
     # backward compatibility
@@ -2649,7 +2649,7 @@ def resume_from_local_or_hf_if_specified(accelerator, args):
 
 
 def get_optimizer(args, trainable_params):
-    # "Optimizer to use: AdamW, AdamW8bit, Lion, SGDNesterov, SGDNesterov8bit, Lion8bit, DAdaptation(DAdaptAdamPreprint), DAdaptAdaGrad, DAdaptAdam, DAdaptAdan, DAdaptAdanIP, DAdaptLion, DAdaptSGD, Adafactor"
+    # "Optimizer to use: AdamW, AdamW8bit, Lion, SGDNesterov, SGDNesterov8bit, PagedAdamW8bit, Lion8bit, PagedLion8bit, DAdaptation(DAdaptAdamPreprint), DAdaptAdaGrad, DAdaptAdam, DAdaptAdan, DAdaptAdanIP, DAdaptLion, DAdaptSGD, Adafactor"
 
     optimizer_type = args.optimizer_type
     if args.use_8bit_adam:
@@ -2726,20 +2726,37 @@ def get_optimizer(args, trainable_params):
         print(f"use Lion optimizer | {optimizer_kwargs}")
         optimizer_class = lion_pytorch.Lion
         optimizer = optimizer_class(trainable_params, lr=lr, **optimizer_kwargs)
-
-    elif optimizer_type == "Lion8bit".lower():
+        
+    elif optimizer_type.endswith("8bit".lower()):
         try:
             import bitsandbytes as bnb
         except ImportError:
             raise ImportError("No bitsandbytes / bitsandbytesがインストールされていないようです")
 
-        print(f"use 8-bit Lion optimizer | {optimizer_kwargs}")
-        try:
-            optimizer_class = bnb.optim.Lion8bit
-        except AttributeError:
-            raise AttributeError(
-                "No Lion8bit. The version of bitsandbytes installed seems to be old. Please install 0.38.0 or later. / Lion8bitが定義されていません。インストールされているbitsandbytesのバージョンが古いようです。0.38.0以上をインストールしてください"
-            )
+        if optimizer_type == "Lion8bit".lower():
+                print(f"use 8-bit Lion optimizer | {optimizer_kwargs}")
+                try:
+                    optimizer_class = bnb.optim.Lion8bit
+                except AttributeError:
+                    raise AttributeError(
+                        "No Lion8bit. The version of bitsandbytes installed seems to be old. Please install 0.38.0 or later. / Lion8bitが定義されていません。インストールされているbitsandbytesのバージョンが古いようです。0.38.0以上をインストールしてください"
+                    )
+        elif optimizer_type == "PagedAdamW8bit".lower():
+                print(f"use 8-bit PagedAdamW optimizer | {optimizer_kwargs}")
+                try:
+                    optimizer_class = bnb.optim.PagedAdamW8bit
+                except AttributeError:
+                    raise AttributeError(
+                        "No PagedAdamW8bit. The version of bitsandbytes installed seems to be old. Please install 0.39.0 or later. / PagedAdamW8bitが定義されていません。インストールされているbitsandbytesのバージョンが古いようです。0.39.0以上をインストールしてください"
+                    )
+        elif optimizer_type == "PagedLion8bit".lower():
+                print(f"use 8-bit Paged Lion optimizer | {optimizer_kwargs}")
+                try:
+                    optimizer_class = bnb.optim.PagedLion8bit
+                except AttributeError:
+                    raise AttributeError(
+                        "No PagedLion8bit. The version of bitsandbytes installed seems to be old. Please install 0.39.0 or later. / PagedLion8bitが定義されていません。インストールされているbitsandbytesのバージョンが古いようです。0.39.0以上をインストールしてください"
+                    )
 
         optimizer = optimizer_class(trainable_params, lr=lr, **optimizer_kwargs)