fixed register_model origin and other imports

lm_eval/api/metrics.py

@@ -118,7 +118,7 @@ def matthews_corrcoef(items):
 
 
 @register_metric(
-    metric="f1_score",
+    metric="f1",
     higher_is_better=True,
     output_type="multiple_choice",
     aggregation="mean",

lm_eval/api/registry.py

@@ -49,9 +49,9 @@ def register_task(name):
 
 def register_group(name):
     def decorate(fn):
-        assert (
-            name not in GROUP_REGISTRY
-        ), f"group named '{name}' conflicts with existing registered group!"
+        # assert (
+        #     name not in GROUP_REGISTRY
+        # ), f"group named '{name}' conflicts with existing registered group!"
 
         func_name = func2task_index[fn.__name__]
         if name in GROUP_REGISTRY:

lm_eval/models/dummy.py

 import random
-from lm_eval.api.model import LM, register_model
+from lm_eval.api.model import LM
+from lm_eval.api.registry import register_model
 
 
 @register_model("dummy")

lm_eval/models/gpt2.py

@@ -7,7 +7,8 @@ import torch.nn.functional as F
 
 from lm_eval import utils
 from lm_eval.logger import eval_logger
-from lm_eval.api.model import LM, register_model
+from lm_eval.api.model import LM
+from lm_eval.api.registry import register_model
 
 from accelerate import Accelerator
 from itertools import islice

lm_eval/models/gpt3.py

@@ -6,7 +6,8 @@ import numpy as np
 
 from tqdm import tqdm
 from lm_eval import utils
-from lm_eval.api.model import LM, register_model
+from lm_eval.api.model import LM
+from lm_eval.api.registry import register_model
 
 
 def get_result(response, ctxlen):

lm_eval/models/textsynth.py

@@ -16,7 +16,8 @@ import os
 import requests as _requests
 import time
 from tqdm import tqdm
-from lm_eval.api.model import LM, register_model
+from lm_eval.api.model import LM
+from lm_eval.api.registry import register_model
 
 
 logger = logging.getLogger(__name__)