Actually it shouldn't be hard to fix it to be compatible with future version

lm_eval/tasks/arithmetic.py

@@ -21,7 +21,7 @@ class Arithmetic(Task):
         url = 'https://raw.githubusercontent.com/openai/gpt-3/master/data/' + file_name
         if not os.path.exists(self.directory):
             os.makedirs(self.directory)
-        download_file(url, self.directory+file_name, checksum)
+        download_file(url, local_file=self.directory+file_name, expected_checksum=checksum)
         self.set_docs()
 
     @abc.abstractmethod

lm_eval/tasks/coqa.py

@@ -16,8 +16,8 @@ class CoQA(Task):
 
         sh ("""mkdir -p data/coqa""")
 
-        download_file("http://downloads.cs.stanford.edu/nlp/data/coqa/coqa-train-v1.0.json", coqa_train_filepath, "b0fdb2bc1bd38dd3ca2ce5fa2ac3e02c6288ac914f241ac409a655ffb6619fa6")
-        download_file("http://downloads.cs.stanford.edu/nlp/data/coqa/coqa-dev-v1.0.json", coqa_dev_filepath, "dfa367a9733ce53222918d0231d9b3bedc2b8ee831a2845f62dfc70701f2540a")
+        download_file("http://downloads.cs.stanford.edu/nlp/data/coqa/coqa-train-v1.0.json", local_file=coqa_train_filepath, expected_checksum="b0fdb2bc1bd38dd3ca2ce5fa2ac3e02c6288ac914f241ac409a655ffb6619fa6")
+        download_file("http://downloads.cs.stanford.edu/nlp/data/coqa/coqa-dev-v1.0.json", local_file=coqa_dev_filepath, expected_checksum="dfa367a9733ce53222918d0231d9b3bedc2b8ee831a2845f62dfc70701f2540a")
 
     def has_training_docs(self):
         return True

lm_eval/tasks/drop.py

@@ -27,7 +27,7 @@ class DROP(Task):
         url = "https://s3-us-west-2.amazonaws.com/allennlp/datasets/drop/drop_dataset.zip"
         checksum = "39d2278a29fd729de301b111a45f434c24834f40df8f4ff116d864589e3249d6"
         zip_path = self.DATASET_PATH / "drop_dataset.zip"
-        download_file(url, str(zip_path), checksum)
+        download_file(url, local_file=str(zip_path), expected_checksum=checksum)
         with ZipFile(zip_path, "r") as zip:
             zip.extractall(self.DATASET_PATH)
 

lm_eval/tasks/hendrycks_ethics.py

@@ -20,7 +20,7 @@ class Ethics(Task):
     def download(self):
         if not os.path.exists('data/ethics/done'):
             sh("mkdir -p data")
-            download_file("https://people.eecs.berkeley.edu/~hendrycks/ethics.tar", "data/ethics.tar", "40acbf1ac0da79a2aabef394d58889136b8d38b05be09482006de2453fb06333")
+            download_file("https://people.eecs.berkeley.edu/~hendrycks/ethics.tar", local_file="data/ethics.tar", expected_checksum="40acbf1ac0da79a2aabef394d58889136b8d38b05be09482006de2453fb06333")
             sh("""
             tar -xf data/ethics.tar -C data/
             rm data/ethics.tar

lm_eval/tasks/hendrycks_math.py

@@ -18,7 +18,7 @@ class Math(Task):
     def download(self):
         if not (self.DATASET_PATH / 'test').exists() or not (self.DATASET_PATH / 'done').exists():
             sh(f"mkdir -p {self.DATASET_PATH}")
-            download_file("https://people.eecs.berkeley.edu/~hendrycks/MATH.tar", f"{self.DATASET_PATH}.tar", "01256fd7cd5430596fdf07e6e6a5827111b5235b7ffed679c662a12f898932da")
+            download_file("https://people.eecs.berkeley.edu/~hendrycks/MATH.tar", local_file=f"{self.DATASET_PATH}.tar", expected_checksum="01256fd7cd5430596fdf07e6e6a5827111b5235b7ffed679c662a12f898932da")
             sh(f"""
             tar -xf {self.DATASET_PATH}.tar -C data/ && touch {self.DATASET_PATH / 'done'}
             rm {self.DATASET_PATH}.tar

lm_eval/tasks/hendrycks_test.py

@@ -45,7 +45,7 @@ class GeneralHendrycksTest(MultipleChoiceTask):
     def download(self):
         if not (self.DATASET_PATH / 'done').exists():
             sh("mkdir -p data")
-            download_file("https://people.eecs.berkeley.edu/~hendrycks/data.tar", "data/data.tar", "78a804365a59028188fb19bd1adcadc5e0c260b220a9d8b2e33a5ea7d5fbe3b4")
+            download_file("https://people.eecs.berkeley.edu/~hendrycks/data.tar", local_file="data/data.tar", expected_checksum="78a804365a59028188fb19bd1adcadc5e0c260b220a9d8b2e33a5ea7d5fbe3b4")
             sh("""
             tar -xf data/data.tar -C data/
             rm data/data.tar

lm_eval/tasks/lambada.py

@@ -14,8 +14,8 @@ class LAMBADA(Task):
             if not os.path.exists("data/lambada/lambada_test.jsonl"):
                 download_file(
                     "http://eaidata.bmk.sh/data/lambada_test.jsonl", 
-                    "data/lambada/lambada_test.jsonl", 
-                    "4aa8d02cd17c719165fc8a7887fddd641f43fcafa4b1c806ca8abc31fabdb226"
+                    local_file="data/lambada/lambada_test.jsonl",
+                    expected_checksum="4aa8d02cd17c719165fc8a7887fddd641f43fcafa4b1c806ca8abc31fabdb226"
                 )
         except:
             # fallback - for some reason best_download doesnt work all the time here

lm_eval/tasks/lambada_multilingual.py

@@ -32,8 +32,8 @@ class MultilingualLAMBADA(lambada.LAMBADA):
         if not os.path.exists(f):
           download_file(
               url, 
-              f, 
-              CHECKSUMS[self.LANG]
+              local_file=f,
+              expected_checksum=CHECKSUMS[self.LANG]
           )
       except:
         # fallback - for some reason best_download doesnt work all the time here

lm_eval/tasks/logiqa.py

@@ -19,7 +19,7 @@ class LogiQA(MultipleChoiceTask):
         ]
         for split in splits:
             file = self.DATASET_PATH / f"{split['name']}.txt"
-            download_file(f"{base_url}/{split['name']}.txt", str(file), split["checksum"])
+            download_file(f"{base_url}/{split['name']}.txt", local_file=str(file), expected_checksum=split["checksum"])
 
     def has_training_docs(self):
         return True

lm_eval/tasks/mutual.py

@@ -36,8 +36,8 @@ class MuTualBase(Task):
         master_zip = Path("data/master.zip")
         download_file(
             "https://github.com/Nealcly/MuTual/archive/master.zip",
-            str(master_zip),
-            "bb325cf6c672f0f02699993a37138b0fa0af6fcfc77ec81dfbe46add4d7b29f9")
+            local_file=str(master_zip),
+            expected_checksum="bb325cf6c672f0f02699993a37138b0fa0af6fcfc77ec81dfbe46add4d7b29f9")
         with zipfile.ZipFile(master_zip, 'r') as zip:
             zip.extractall("data")
         Path("data/MuTual-master/data").rename(str(self.BASE_PATH))

lm_eval/tasks/pile.py

@@ -19,8 +19,8 @@ class PilePerplexityTask(PerplexityTask, abc.ABC):
     def download(self):
         # TODO: separate pile val/test out by component so we don't have to scan the entire file once per set
         os.makedirs("data/pile/", exist_ok=True)
-        download_file("https://the-eye.eu/public/AI/pile/val.jsonl.zst", self.VAL_PATH, "264c875d8bbd355d8daa9d032b75fd8fb91606218bb84dd1155b203fcd5fab92")
-        download_file("https://the-eye.eu/public/AI/pile/test.jsonl.zst", self.TEST_PATH, "0bb28c52d0b5596d389bf179ce2d43bf7f7ffae76b0d2d20b180c97f62e0975e")
+        download_file("https://the-eye.eu/public/AI/pile/val.jsonl.zst", local_file=self.VAL_PATH, expected_checksum="264c875d8bbd355d8daa9d032b75fd8fb91606218bb84dd1155b203fcd5fab92")
+        download_file("https://the-eye.eu/public/AI/pile/test.jsonl.zst", local_file=self.TEST_PATH, expected_checksum="0bb28c52d0b5596d389bf179ce2d43bf7f7ffae76b0d2d20b180c97f62e0975e")
 
     def validation_docs(self):
         rdr = lm_dataformat.Reader(self.VAL_PATH)

lm_eval/tasks/qa4mre.py

@@ -32,8 +32,8 @@ class QA4MRE(MultipleChoiceTask):
         if not os.path.isfile(f"data/qa4mre/QA4MRE-{year}-{lang}"):
             download_file(
                 url_path,
-                f"data/qa4mre/QA4MRE-{year}-{lang}_GS.xml",
-                sha256sums[year],
+                local_file=f"data/qa4mre/QA4MRE-{year}-{lang}_GS.xml",
+                expected_checksum=sha256sums[year],
                 )
 
     def has_training_docs(self):

lm_eval/tasks/sciq.py

@@ -13,8 +13,8 @@ class SciQ(MultipleChoiceTask):
             os.makedirs('data/sciq', exist_ok=True)
             download_file(
                 'https://ai2-public-datasets.s3.amazonaws.com/sciq/SciQ.zip',
-                'data/sciq/SciQ.zip', 
-                '7f3312f6ac6b09970b32942d106a8c44ec0dad46a0369f17d635aff8e348a87c',
+                local_file='data/sciq/SciQ.zip',
+                expected_checksum='7f3312f6ac6b09970b32942d106a8c44ec0dad46a0369f17d635aff8e348a87c',
             )
             with zipfile.ZipFile("data/sciq/SciQ.zip", "r") as zf:
                 zf.extractall("data/sciq/")

lm_eval/tasks/triviaqa.py

@@ -12,7 +12,7 @@ class TriviaQA(Task):
     def download(self):
         if not os.path.exists('data/triviaqa/unfiltered-web-train.jsonl'):
             os.makedirs("data/triviaqa/", exist_ok=True)
-            download_file("http://eaidata.bmk.sh/data/triviaqa-unfiltered.tar.gz", "data/triviaqa/triviaqa-unfiltered.tar.gz", "adc19b42769062d241a8fbe834c56e58598d9322eb6c614e9f33a68a2cf5523e")
+            download_file("http://eaidata.bmk.sh/data/triviaqa-unfiltered.tar.gz", local_file="data/triviaqa/triviaqa-unfiltered.tar.gz", expected_checksum="adc19b42769062d241a8fbe834c56e58598d9322eb6c614e9f33a68a2cf5523e")
             sh("""
             cd data/triviaqa/
             tar -xf triviaqa-unfiltered.tar.gz

lm_eval/tasks/truthfulqa.py

@@ -58,7 +58,7 @@ class TruthfulQAMultipleChoice(Task):
         Path.mkdir(self.DATASET_PATH, parents=True)
         mc_url = "https://raw.githubusercontent.com/sylinrl/TruthfulQA/013686a06be7a7bde5bf8223943e106c7250123c/data/mc_task.json"
         checksum = "6eb4125d25750c0145c4be2dce00440736684ab6f74ce6bff2139571cc758954"
-        download_file(mc_url, str(self.DATASET_PATH / "mc_task.json"), checksum)
+        download_file(mc_url, local_file=str(self.DATASET_PATH / "mc_task.json"), expected_checksum=checksum)
 
     def has_training_docs(self):
         return False
@@ -163,7 +163,7 @@ class TruthfulQAGeneration(Task):
         Path.mkdir(self.DATASET_PATH, parents=True)
         url = "https://raw.githubusercontent.com/sylinrl/TruthfulQA/013686a06be7a7bde5bf8223943e106c7250123c/TruthfulQA.csv"
         checksum = "8d7dd15f033196140f032d97d30f037da7a7b1192c3f36f9937c1850925335a2"
-        download_file(url, str(self.DATASET_PATH / "TruthfulQA.csv"), checksum)
+        download_file(url, local_file=str(self.DATASET_PATH / "TruthfulQA.csv"), expected_checksum=checksum)
 
     def has_training_docs(self):
         return False

lm_eval/tasks/unscramble.py

@@ -29,7 +29,7 @@ class WordUnscrambleTask(Task):
         if not file.exists():
             rawfile = file.parent / (file.name + ".gz")
             base_url = "https://raw.githubusercontent.com/openai/gpt-3/master/data"
-            download_file(f"{base_url}/{self.FILENAME}.gz", str(rawfile), self.CHECKSUM)
+            download_file(f"{base_url}/{self.FILENAME}.gz", local_file=str(rawfile), expected_checksum=self.CHECKSUM)
             extract_gzip(gz=rawfile, to=file)
 
     def has_training_docs(self):

lm_eval/tasks/wikitext.py

@@ -46,7 +46,7 @@ class WikiText(PerplexityTask):
     def download(self):
         if not os.path.exists('data/wikitext/wikitext-2-raw/wiki.valid.raw'):
             os.makedirs("data/wikitext/", exist_ok=True)
-            download_file("https://s3.amazonaws.com/research.metamind.io/wikitext/wikitext-2-raw-v1.zip", "data/wikitext/wikitext-2-raw-v1.zip", "ef7edb566e3e2b2d31b29c1fdb0c89a4cc683597484c3dc2517919c615435a11")
+            download_file("https://s3.amazonaws.com/research.metamind.io/wikitext/wikitext-2-raw-v1.zip", local_file="data/wikitext/wikitext-2-raw-v1.zip", expected_checksum="ef7edb566e3e2b2d31b29c1fdb0c89a4cc683597484c3dc2517919c615435a11")
             sh("cd data/wikitext/ && unzip wikitext-2-raw-v1.zip")
 
     def fewshot_description(self):

setup.py

@@ -21,7 +21,7 @@ setuptools.setup(
     python_requires='>=3.6',
     install_requires=[
         "black",
-        "best_download>=0.0.6,<0.0.8",
+        "best_download>=0.0.6",
         "datasets==1.15.1",
         "click>=7.1",
         "scikit-learn>=0.24.1",