diff --git a/.github/workflows/run_eval_tests.yml b/.github/workflows/run_eval_tests.yml
new file mode 100644
index 000000000..3c47f43a0
--- /dev/null
+++ b/.github/workflows/run_eval_tests.yml
@@ -0,0 +1,40 @@
+name: Run Unit Tests for Evaluation scripts via Pytest
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  test:
+    name: Run Tests
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2.4.0
+        with:
+          fetch-depth: 0
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v2.3.1
+        with:
+          python-version: 3.11
+      - id: cache-dependencies
+        name: Cache dependencies
+        uses: actions/cache@v2.1.7
+        with:
+          path: ${{ github.workspace }}/.venv
+          key: dependencies-${{ hashFiles('**/poetry.lock') }}
+          restore-keys: dependencies-
+      - name: Install dependencies
+        if: steps.cache-dependencies.cache-hit != 'true'
+        run: |
+          python3 -m pip install -U pip poetry
+          poetry --version
+          poetry check --no-interaction
+          poetry config virtualenvs.in-project true
+          poetry install --no-interaction
+      - name: Run tests
+        run: |
+          poetry run pytest -ra -s tests
diff --git a/Database/gold/ImpactDB_DataTable_Validation.xlsx b/Database/gold/ImpactDB_DataTable_Validation.xlsx
index 9a243cb63..1d5c6cf13 100644
Binary files a/Database/gold/ImpactDB_DataTable_Validation.xlsx and b/Database/gold/ImpactDB_DataTable_Validation.xlsx differ
diff --git a/Database/gold/gold_from_excel/Affected.parquet b/Database/gold/gold_from_excel/Affected.parquet
deleted file mode 100644
index ab2283090..000000000
--- a/Database/gold/gold_from_excel/Affected.parquet
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:04cf088bd965b9c65af9e28b2427e64d0acbada0fdb67b9f956b12321be5f4bc
-size 27316
diff --git a/Database/gold/gold_from_excel/Buildings_Damaged.parquet b/Database/gold/gold_from_excel/Buildings_Damaged.parquet
deleted file mode 100644
index 21f800396..000000000
--- a/Database/gold/gold_from_excel/Buildings_Damaged.parquet
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6536b9f8e83bac69a746f0e12afec9dde21ab1e0bb740c06952ba8245a500dd8
-size 28526
diff --git a/Database/gold/gold_from_excel/Damage.parquet b/Database/gold/gold_from_excel/Damage.parquet
deleted file mode 100644
index 680b7f4c9..000000000
--- a/Database/gold/gold_from_excel/Damage.parquet
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:33397cf34322b3713754580e9fdac2597264380bb9dc02ec956d723b19bf90da
-size 29985
diff --git a/Database/gold/gold_from_excel/Deaths.parquet b/Database/gold/gold_from_excel/Deaths.parquet
deleted file mode 100644
index ddf839d9d..000000000
--- a/Database/gold/gold_from_excel/Deaths.parquet
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f008ca007eb1c12a9b94899df06d50aaf7771710743e35af322004254b2ba1e7
-size 28477
diff --git a/Database/gold/gold_from_excel/Displaced.parquet b/Database/gold/gold_from_excel/Displaced.parquet
deleted file mode 100644
index 7da37003b..000000000
--- a/Database/gold/gold_from_excel/Displaced.parquet
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:61f0a601dfb9191c17b42050a3d414edf9629583a79a708889077c34f40a84bb
-size 27660
diff --git a/Database/gold/gold_from_excel/Events.parquet b/Database/gold/gold_from_excel/Events.parquet
deleted file mode 100644
index 696474fe0..000000000
--- a/Database/gold/gold_from_excel/Events.parquet
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:86155cdf45bc57dfee0c8508da5f704abef572334652d0408a46b6b0ea6c93ce
-size 40090
diff --git a/Database/gold/gold_from_excel/Homeless.parquet b/Database/gold/gold_from_excel/Homeless.parquet
deleted file mode 100644
index 7ee79297b..000000000
--- a/Database/gold/gold_from_excel/Homeless.parquet
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:45e933c3d06ba8ecc8dba20349cab8864d32cd11247bff693bfc633df1c16095
-size 27116
diff --git a/Database/gold/gold_from_excel/Injured.parquet b/Database/gold/gold_from_excel/Injured.parquet
deleted file mode 100644
index b27d720a9..000000000
--- a/Database/gold/gold_from_excel/Injured.parquet
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9e0045f950ff2d740bb506183ec8fb1493da5643d10ace107234db976eb074ee
-size 27320
diff --git a/Database/gold/gold_from_excel/Insured_Damage.parquet b/Database/gold/gold_from_excel/Insured_Damage.parquet
deleted file mode 100644
index 571eb7bc8..000000000
--- a/Database/gold/gold_from_excel/Insured_Damage.parquet
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7b7799dcee9ed7c84ebd9fee1bca6b150b29025df1dec0d6dd5c0e953034421d
-size 28771
diff --git a/Database/gold/specific_instances/Affected.parquet b/Database/gold/specific_instances/Affected.parquet
new file mode 100644
index 000000000..d6662437a
--- /dev/null
+++ b/Database/gold/specific_instances/Affected.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb361a5a29bf3e1643b7b2b6c21694857b1041c796477b4724a5503f1b649c98
+size 28742
diff --git a/Database/gold/specific_instances/Buildings_Damaged.parquet b/Database/gold/specific_instances/Buildings_Damaged.parquet
new file mode 100644
index 000000000..d0333a37d
--- /dev/null
+++ b/Database/gold/specific_instances/Buildings_Damaged.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e831bdddee5f3213a72ae131e6ea855d4f6685582b21577d20759252cad3fe
+size 29952
diff --git a/Database/gold/specific_instances/Damage.parquet b/Database/gold/specific_instances/Damage.parquet
new file mode 100644
index 000000000..e89ae8efe
--- /dev/null
+++ b/Database/gold/specific_instances/Damage.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84e7bf563c5f02dc15a3e259e8d3b3c186ab4025fd30b8ac6dfb325a7c4dfd19
+size 31411
diff --git a/Database/gold/specific_instances/Deaths.parquet b/Database/gold/specific_instances/Deaths.parquet
new file mode 100644
index 000000000..25675ede2
--- /dev/null
+++ b/Database/gold/specific_instances/Deaths.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade788503ddf610051387b91266a4eac0b7568092e48290d8151d7e8df56e729
+size 29903
diff --git a/Database/gold/specific_instances/Displaced.parquet b/Database/gold/specific_instances/Displaced.parquet
new file mode 100644
index 000000000..032e0379b
--- /dev/null
+++ b/Database/gold/specific_instances/Displaced.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce776a668ab63f42b93ad4968aba57cec0f88148c818d93554493b8e33600ab
+size 29086
diff --git a/Database/gold/specific_instances/Events.parquet b/Database/gold/specific_instances/Events.parquet
new file mode 100644
index 000000000..c40daa37a
--- /dev/null
+++ b/Database/gold/specific_instances/Events.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61ad566b2afcf68ea6a094345ffdb7f8ccb97cc7937ba76c296bbedc799670cd
+size 42799
diff --git a/Database/gold/specific_instances/Homeless.parquet b/Database/gold/specific_instances/Homeless.parquet
new file mode 100644
index 000000000..ccd044e6a
--- /dev/null
+++ b/Database/gold/specific_instances/Homeless.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2468c5305c93f9a6f88ca617e1b7e0dc123b64f129d2948cf98ba57f35002e
+size 28542
diff --git a/Database/gold/specific_instances/Injured.parquet b/Database/gold/specific_instances/Injured.parquet
new file mode 100644
index 000000000..37da394c9
--- /dev/null
+++ b/Database/gold/specific_instances/Injured.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96cb177948896be74f3d046f999664ab2ba42d3ff6016a439d356da93b64a6cd
+size 28746
diff --git a/Database/gold/specific_instances/Insured_Damage.parquet b/Database/gold/specific_instances/Insured_Damage.parquet
new file mode 100644
index 000000000..b2f382664
--- /dev/null
+++ b/Database/gold/specific_instances/Insured_Damage.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d0697c096c2ad53131c629dd7c85626cbd006a7c604244fdb61e2ccbb3fa1d
+size 30197
diff --git a/Database/gold_from_excel.py b/Database/gold_from_excel.py
index a8cc109a9..316c73c44 100644
--- a/Database/gold_from_excel.py
+++ b/Database/gold_from_excel.py
@@ -1,9 +1,10 @@
-import pathlib
 import argparse
+import pathlib
 import re
 
 import pandas as pd
-from scr.normalize_utils import Logging
+
+from Database.scr.normalize_utils import Logging
 
 pd.set_option("display.max_rows", None)
 pd.set_option("display.max_columns", None)
@@ -58,6 +59,7 @@ def flatten(xss):
 # main and specific impact events have these three column sets in common
 shared_cols = [
     "Event_ID",
+    "Event_ID_decimal",
     "Source",
     "Event_Name",
 ]
@@ -115,7 +117,8 @@ def flatten(xss):
 for i in ["Insured_Damage", "Damage"]:
     convert_to_boolean.extend([x for x in specific_impacts_columns[i] if "_Adjusted" in x and "_Year" not in x])
 
-convert_to_float = ["Event_ID"]
+convert_to_float = ["Event_ID_decimal"]
+
 
 def flatten_data_table():
     logger.info("Loading excel file...")
@@ -197,7 +200,7 @@ def flatten_data_table():
         )
 
     logger.info("Splitting main events from specific impact")
-    data_table["main"] = data_table.Event_ID.apply(lambda x: float(x).is_integer())
+    data_table["main"] = data_table.Event_ID_decimal.apply(lambda x: float(x).is_integer())
     data_table["main"].value_counts()
 
     logger.info("Storing Main Events table")
@@ -271,4 +274,4 @@ def flatten_data_table():
     logger.info(f"Creating {args.output_dir} if it does not exist!")
     pathlib.Path(args.output_dir).mkdir(parents=True, exist_ok=True)
 
-    flatten_data_table()
\ No newline at end of file
+    flatten_data_table()
diff --git a/Database/merge_json_output.py b/Database/merge_json_output.py
index 3235bed5f..93137fb0c 100644
--- a/Database/merge_json_output.py
+++ b/Database/merge_json_output.py
@@ -1,6 +1,7 @@
 import argparse
 import pathlib
-from scr.normalize_utils import Logging, NormalizeJsonOutput
+
+from Database.scr.normalize_utils import Logging, NormalizeJsonOutput
 
 if __name__ == "__main__":
     logger = Logging.get_logger("merge-mixtral-or-mistral-output")
@@ -34,7 +35,7 @@
     logger.info(args)
 
     logger.info(f"Creating {args.output_dir} if it does not exist!")
-    pathlib.Path(args.output_dir).mkdir(parents=True, exist_ok=True) 
+    pathlib.Path(args.output_dir).mkdir(parents=True, exist_ok=True)
 
     json_utils = NormalizeJsonOutput()
     dfs = json_utils.merge_json(args.input_dir)
diff --git a/Database/output/nlp4climate/README.md b/Database/output/README.md
similarity index 73%
rename from Database/output/nlp4climate/README.md
rename to Database/output/README.md
index c9ccf1eb5..b5d68ce71 100644
--- a/Database/output/nlp4climate/README.md
+++ b/Database/output/README.md
@@ -1,5 +1,7 @@
 #### Post-processed files
 
+This is where parsed LLM outputs are stored in .parquet
+
 Suggested breakdown:
 
 ```shell
@@ -8,8 +10,8 @@ Suggested breakdown:
 └── nlp4climate # <-- ℹ️ Broader name to group experiments
     ├── dev # <-- ℹ️ dev set, specific to this group of experiments
     │   ├── gpt4_experiment.parquet
-    │   └── mistral_experiment.json
+    │   └── mistral_experiment.parquet
     └── test # <-- ℹ️ test set, specific to this group of experiments
         ├── gpt4_experiment.parquet
-        └── mistral_experiment.json
+        └── mistral_experiment.parquet
 ```
diff --git a/Database/parse_events.py b/Database/parse_events.py
index f17ddbb58..a7eac14f8 100644
--- a/Database/parse_events.py
+++ b/Database/parse_events.py
@@ -1,11 +1,12 @@
 import argparse
-import re
 import pathlib
+import re
+
 import pandas as pd
 
-from scr.normalize_locations import NormalizeLocation
-from scr.normalize_numbers import NormalizeNumber
-from scr.normalize_utils import Logging, NormalizeUtils
+from Database.scr.normalize_locations import NormalizeLocation
+from Database.scr.normalize_numbers import NormalizeNumber
+from Database.scr.normalize_utils import Logging, NormalizeUtils
 
 if __name__ == "__main__":
     logger = Logging.get_logger("parse_events")
@@ -81,7 +82,7 @@
     logger.info(f"Passed args: {args}")
 
     logger.info(f"Creating {args.output_dir} if it does not exist!")
-    pathlib.Path(args.output_dir).mkdir(parents=True, exist_ok=True) 
+    pathlib.Path(args.output_dir).mkdir(parents=True, exist_ok=True)
 
     utils = NormalizeUtils()
     nlp = utils.load_spacy_model(args.spaCy_model_name)
@@ -138,7 +139,7 @@
             logger.info(f"Normalizing boolean column {inflation_adjusted_col}")
             events[inflation_adjusted_col] = events[inflation_adjusted_col].replace(
                 {_no: False, _yes: True}, regex=True
-                )
+            )
 
         logger.info("Normalizing nulls")
         events = utils.replace_nulls(events)
@@ -203,7 +204,6 @@
             )
 
         if args.location_column in events.columns and args.country_column in events.columns:
-
             logger.info("Normalizing Locations")
             events["Location_Tmp"] = events["Location"].apply(
                 lambda locations: (
@@ -312,9 +312,11 @@
 
             sub_event = pd.concat([sub_event.Event_ID, sub_event[col].apply(pd.Series)], axis=1)
 
-            logger.info(f"Dropping any columns with non-str column names due to None types in the dicts {[c for c in sub_event.columns if not isinstance(c, str)]}")
+            logger.info(
+                f"Dropping any columns with non-str column names due to None types in the dicts {[c for c in sub_event.columns if not isinstance(c, str)]}"
+            )
             sub_event = sub_event[[c for c in sub_event.columns if isinstance(c, str)]]
-            
+
             logger.info(f"Normalizing nulls for subevent {col}")
             sub_event = utils.replace_nulls(sub_event)
 
@@ -322,7 +324,7 @@
                 col
                 for col in sub_event.columns
                 if col.startswith("Num_")
-                or col.endswith("_Damage")
+                or col.endswith("Damage")
                 and "Date" not in col
                 and args.location_column not in col
             ]
@@ -389,10 +391,10 @@
                 lambda country: (norm_loc.get_gadm_gid(country=country) if country else None)
             )
 
-            '''
+            """
             logger.info(f"Dropping columns with no locations for subevent {col}")
             sub_event.dropna(subset=[f"Location_{location_col}"], how="all", inplace=True)
-            '''
+            """
             logger.info(f"Normalizing location names for subevent {col}")
             sub_event[
                 [
@@ -427,7 +429,7 @@
             )
 
             def normalize_location_rows_if_country(row):
-            # if location and country are identical in subevents, generalize country normalization
+                # if location and country are identical in subevents, generalize country normalization
                 if row[f"Location_{location_col}"] == row[args.country_column]:
                     for i in ["Norm", "Type", "GeoJson", "GID"]:
                         row[f"Location_{location_col}_{i}"] = row[f"Country_{i}"]
diff --git a/Database/scr/normalize_locations.py b/Database/scr/normalize_locations.py
index 961f107af..ad4af6674 100644
--- a/Database/scr/normalize_locations.py
+++ b/Database/scr/normalize_locations.py
@@ -485,7 +485,7 @@ def get_gadm_gid(
     @staticmethod
     def extract_locations(
         text: str,
-    ) -> tuple[list] | None:
+    ) -> tuple[list[str]]:
         """
         Extracts countries and sublocations from the '|, &' string format
         Example:
@@ -496,7 +496,7 @@ def extract_locations(
         try:
             split_by_pipe = text.split("|")
         except BaseException:
-            return
+            return [], []
         try:
             if split_by_pipe:
                 for s in split_by_pipe:
@@ -507,7 +507,7 @@ def extract_locations(
                     locations.extend([locations_tmp])
             return countries, locations
         except BaseException:
-            return
+            return [], []
 
     def _debug(self, response):
         self.logger.debug(type(response))
diff --git a/Evaluation/__init__.py b/Evaluation/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/Evaluation/comparer.py b/Evaluation/comparer.py
index ebd1636b1..00aa7a8fb 100644
--- a/Evaluation/comparer.py
+++ b/Evaluation/comparer.py
@@ -1,4 +1,4 @@
-import normaliser
+from Evaluation.normaliser import Normaliser
 
 
 class Comparer:
@@ -8,7 +8,7 @@ def __init__(self, null_penalty: bool, target_columns: list[str]):
         """Initialisation."""
         # Penalty score if one field is None, but not the other
         self.null_penalty = null_penalty
-        self.norm = normaliser.Normaliser()
+        self.norm = Normaliser()
         self.target_columns = target_columns
 
     def target_col(self, l) -> list:
diff --git a/Evaluation/evaluator.py b/Evaluation/evaluator.py
index 3fb7a851b..3b19f6e5c 100644
--- a/Evaluation/evaluator.py
+++ b/Evaluation/evaluator.py
@@ -4,11 +4,13 @@
 import pathlib
 from pprint import pformat, pprint
 
-import comparer
 import numpy as np
 import pandas as pd
-from utils import Logging
-from weights import weights as weights_dict
+
+from Evaluation.comparer import Comparer
+from Evaluation.matcher import SpecificInstanceMatcher
+from Evaluation.utils import Logging
+from Evaluation.weights import weights as weights_dict
 
 if __name__ == "__main__":
     logger = Logging.get_logger("evaluator")
@@ -67,12 +69,35 @@
         type=str,
     )
 
+    parser.add_argument(
+        "-t",
+        "--event_type",
+        dest="event_type",
+        default="main",
+        choices=["main", "sub"],
+        help="Choose which events to parse. Possible values: main or sub",
+        type=str,
+    )
+
+    parser.add_argument(
+        "-si",
+        "--specific_instance_type",
+        dest="specific_instance_type",
+        default="specific_instance",
+        help="""Supply the specific instance type/category (example: 'deaths', 'insurance_damage')
+            to store matched specific instances for gold and sys""",
+        type=str,
+        required=False,
+    )
+
     args = parser.parse_args()
 
     output_dir = f"Database/evaluation_results/{args.model_name}"
     logger.info(f"Creating {output_dir} if it does not exist!")
     pathlib.Path(output_dir).mkdir(parents=True, exist_ok=True)
 
+    matcher = SpecificInstanceMatcher()
+
     gold = pd.read_parquet(args.gold_set_filepath, engine="fastparquet").replace(
         {np.nan: None, "NULL ": None, "NULL": None}
     )
@@ -81,8 +106,41 @@
         {np.nan: None, "NULL ": None, "NULL": None}
     )
 
-    logger.info("Only including events in the gold file")
-    sys = sys[sys.Event_ID.isin(gold["Event_ID"].to_list())]
+    if args.event_type == "sub":
+        logger.info("Pairing up specific instances ('sub-events')")
+        event_ids = set(list(gold.Event_ID.unique()) + list(sys.Event_ID.unique()))
+        si_gold, si_sys = [], []
+
+        for gold_list, sys_list in zip(
+            [
+                gold[gold.Event_ID == e_id][weights_dict[args.weights_config].keys()].to_dict(orient="records")
+                for e_id in event_ids
+            ],
+            [
+                sys[sys.Event_ID == e_id][weights_dict[args.weights_config].keys()].to_dict(orient="records")
+                for e_id in event_ids
+            ],
+        ):
+            gold_out, sys_out = matcher.match(gold_list, sys_list)
+            si_gold.extend(gold_out)
+            si_sys.extend(sys_out)
+
+        if len(si_gold) != len(si_sys):
+            logger.error(
+                f"The length of the gold data does not match the length of the sys data '{len(gold)}!={len(sys)}'"
+            )
+            exit()
+
+        gold, sys = pd.DataFrame(si_gold).replace({np.nan: None, "NULL ": None, "NULL": None}), pd.DataFrame(
+            si_sys
+        ).replace({np.nan: None, "NULL ": None, "NULL": None})
+
+        gold.to_parquet(f"{output_dir}/gold_{args.specific_instance_type}.parquet")
+        sys.to_parquet(f"{output_dir}/sys_{args.specific_instance_type}.parquet")
+
+    if args.event_type == "main":
+        logger.info("Only including events in the gold file!")
+        sys = sys[sys.Event_ID.isin(gold["Event_ID"].to_list())]
 
     logger.info(f"The following events exist in gold: {pprint(list(gold['Event_ID'].unique()), indent=10)}")
 
@@ -93,7 +151,7 @@
         elif "URL" in sys.columns:
             source_col_sys = "URL"
         else:
-            logger.info("No source column found... exiting.")
+            logger.info("No source column found to determine article source... exiting.")
             exit()
 
         sys["Article_From"] = sys[source_col_sys].apply(lambda x: "artemis" if "artemis" in x else "wikipedia")
@@ -111,26 +169,27 @@
 
         logger.info(f"Evaluation limited to {sys.shape} events from source {args.score}")
 
-    # Add dummy rows for missing events
-    missing_ids = set(sys["Event_ID"].to_list()) ^ set(gold["Event_ID"].to_list())
-    if missing_ids:
-        logger.info(
-            f"Missing events! {missing_ids}. The columns in these events will be constructed with `NoneType` objects. The system output will be penalized for missing events with the selected null penalty ({args.null_penalty})"
-        )
-        gold_cols = list(gold.columns)
-        rows_to_add = []
-        for event_id in missing_ids:
-            # Create a dictionary for the new row with all columns set to "" except Country_Norm which excepts a list
-            new_row = {col: None for col in gold_cols}
-            for col in ["Country_Norm", "Location_Norm"]:
-                if col in gold_cols:
-                    new_row[col] = "[]"
-            new_row["Event_ID"] = event_id  # Set the 'Event_ID'
-            rows_to_add.append(new_row)
-
-        missing_rows = pd.DataFrame(rows_to_add)
-        sys = pd.concat([sys, missing_rows], ignore_index=True).sort_values("Event_ID")
-        sys.replace({np.nan: None}, inplace=True)
+    if args.event_type == "main":
+        # Add dummy rows for missing events (for main event evaluation only)
+        missing_ids = set(sys["Event_ID"].to_list()) ^ set(gold["Event_ID"].to_list())
+        if missing_ids:
+            logger.info(
+                f"Missing events! {missing_ids}. The columns in these events will be constructed with `NoneType` objects. The system output will be penalized for missing events with the selected null penalty ({args.null_penalty})"
+            )
+            gold_cols = list(gold.columns)
+            rows_to_add = []
+            for event_id in missing_ids:
+                # Create a dictionary for the new row with all columns set to "" except Country_Norm which excepts a list
+                new_row = {col: None for col in gold_cols}
+                for col in ["Country_Norm", "Location_Norm"]:
+                    if col in gold_cols:
+                        new_row[col] = "[]"
+                new_row["Event_ID"] = event_id  # Set the 'Event_ID'
+                rows_to_add.append(new_row)
+
+            missing_rows = pd.DataFrame(rows_to_add)
+            sys = pd.concat([sys, missing_rows], ignore_index=True).sort_values("Event_ID")
+            sys.replace({np.nan: None}, inplace=True)
 
     # Specify null penalty
     null_penalty = args.null_penalty
@@ -147,17 +206,20 @@
     logger.info(f"Chosen weights:\n {pformat(weights)}")
 
     # Instantiate comparer
-    comp = comparer.Comparer(null_penalty, target_columns=weights.keys())
+    comp = Comparer(null_penalty, target_columns=weights.keys())
     logger.info(f"Target columns: {comp.target_columns}")
 
-    sys = sys.sort_values("Event_ID")
-    gold = gold.sort_values("Event_ID")
+    if args.event_type == "main":
+        # sort by "Event_ID" only for main event evaluation
+        sys = sys.sort_values("Event_ID")
+        gold = gold.sort_values("Event_ID")
 
-    for col in ["Country_Norm", "Location_Norm"]:
+    list_type_cols = ["Country_Norm", "Location_Norm"] if args.event_type == "main" else ["Location_Norm"]
+    for col in list_type_cols:
         if col in sys.columns:
-            sys[col] = sys[col].apply(ast.literal_eval)
+            sys[col] = sys[col].apply(lambda x: ast.literal_eval(x) if isinstance(x, str) else x)
         if col in gold.columns:
-            gold[col] = gold[col].apply(ast.literal_eval)
+            gold[col] = gold[col].apply(lambda x: ast.literal_eval(x) if isinstance(x, str) else x)
 
     logger.info("Parsed strings to lists or dicts")
 
@@ -169,7 +231,12 @@
     logger.info(f"Prepared {len(sys_data)} events for evaluation")
 
     comps = [
-        [sys["Event_ID"], gold["Event_ID"], comp.weighted(sys, gold, weights), comp.all(sys, gold)]
+        [
+            sys["Event_ID"],
+            gold["Event_ID"],
+            comp.weighted(sys, gold, weights),
+            comp.all(sys, gold),
+        ]
         for (sys, gold) in pairs
     ]
     all_comps = pd.DataFrame(
@@ -178,15 +245,33 @@
     ).replace({np.nan: None})
 
     all_comps.sort_values("Weighted_Score")
-    all_comps.to_csv(f"{output_dir}/{args.score}_{len(sys_data)}_results.csv", index=False)
-
+    if args.event_type == "main":
+        all_comps.to_csv(f"{output_dir}/{args.score}_{len(sys_data)}_results.csv", index=False)
+    elif args.event_type == "sub":
+        all_comps.to_csv(
+            f"{output_dir}/{args.score}_{len(sys_data)}_{args.specific_instance_type}_results.csv", index=False
+        )
     averages = {}
     for i in all_comps.columns:
         if not i.startswith("Event_ID"):
             averages[i] = all_comps.loc[:, i].mean()
 
-    avg_result_filename = f"{output_dir}/{args.score}_{len(sys_data)}_avg_results.json"
+    if args.event_type == "main":
+        avg_result_filename = f"{output_dir}/{args.score}_{len(sys_data)}_avg_results.json"
+    elif args.event_type == "sub":
+        avg_result_filename = (
+            f"{output_dir}/{args.score}_{len(sys_data)}_{args.specific_instance_type}_avg_results.json"
+        )
+
     with open(avg_result_filename, "w") as f:
         json.dump(averages, f)
 
+    # get average per event_ID when evaluating specific instances
+    if args.event_type == "sub":
+        all_comps["Event_ID"] = all_comps["Event_ID1"].apply(lambda x: x.split("-")[0])
+        all_comps.groupby("Event_ID")[[c for c in all_comps.columns if not c.startswith("Event_ID")]].mean().to_csv(
+            f"{output_dir}/{args.score}_{len(sys_data)}_{args.specific_instance_type}_avg_per_event_id_results.csv",
+            index=False,
+        )
+
     logger.info(f"Done! Results in {avg_result_filename}")
diff --git a/Evaluation/matcher.py b/Evaluation/matcher.py
new file mode 100644
index 000000000..04f8e2146
--- /dev/null
+++ b/Evaluation/matcher.py
@@ -0,0 +1,134 @@
+from statistics import mean
+
+from Evaluation.comparer import Comparer
+from Evaluation.utils import Logging
+
+
+class SpecificInstanceMatcher:
+    """Matches and pads specific instances (subevents) from two separate lists.
+    'Padded' specific instances will have NoneType objects as values"""
+
+    def __init__(self, threshold: float = 0.6, null_penalty: float = 0.5):
+        self.logger = Logging.get_logger("specific instance matcher")
+
+        self.threshold = threshold
+        self.int_cat: list[str] = [
+            "Num_Min",
+            "Num_Max",
+            "Adjusted_Year",
+            "Start_Date_Day",
+            "Start_Date_Month",
+            "Start_Date_Year",
+            "End_Date_Day",
+            "End_Date_Month",
+            "End_Date_Year",
+        ]
+        self.bool_cat: list[str] = ["Adjusted"]
+        self.str_cat: list[str] = ["Country_Norm", "Unit"]
+        self.list_cat: list[str] = ["Location_Norm"]
+
+        self.comp = Comparer(null_penalty, [])
+
+    @staticmethod
+    def create_pad(specific_instance: dict) -> dict:
+        padded = {}
+        for k in specific_instance.keys():
+            # preserve "Event_D"
+            padded[k] = specific_instance[k] if k == "Event_ID" else None
+        return padded
+
+    def calc_similarity(self, gold_instance: dict, sys_list: list) -> list[float]:
+        score_list: float = []
+        for si in sys_list:
+            scores = []
+            for k in gold_instance.keys():
+                if k in self.int_cat:
+                    r = self.comp.integer(gold_instance[k], si[k])
+                elif k in self.bool_cat:
+                    r = self.comp.boolean(gold_instance[k], si[k])
+                elif k in self.str_cat:
+                    r = self.comp.string(gold_instance[k], si[k])
+                elif k in self.list_cat:
+                    r = self.comp.sequence(gold_instance[k], si[k])
+                try:
+                    scores.append(1 - r)
+                    del r
+                except Exception:
+                    if k != "Event_ID":
+                        self.logger.warning(f"Unsupported column name: {k} will be ignored during matching.")
+
+            score_list.append(mean(scores))
+
+        # index of mean score corresponds to sys_list item
+        return score_list
+
+    def schema_checker(self, gold_list: list[dict], sys_list: list[dict]) -> bool:
+        # in case the sys output or gold is an empty list
+        if len(gold_list) == 0 or len(sys_list) == 0:
+            return True
+
+        for g in range(len(gold_list)):
+            # check that all column names in the gold are consistent
+            if sorted(gold_list[0].keys()) != sorted(gold_list[g].keys()):
+                self.logger.error(
+                    f"Gold file contains entries with inconsistent column names at specific instance #{g}: {gold_list[g].keys()}. Expected columns: {gold_list[0].keys()}"
+                )
+                return False
+
+        for s in range(len(sys_list)):
+            # if all gold columns are consistent, check that they are consistent with the sys_list ones
+            try:
+                assert all([e in sys_list[s].keys() for e in gold_list[0].keys()])
+                return True
+            except Exception:
+                self.logger.error(
+                    f"Inconsistent columns found in sys file!: {[e for e in sys_list[s].keys() if e not in gold_list[0].keys()]}"
+                )
+                return False
+
+    def match(self, gold_list: list[dict], sys_list: list[dict]) -> tuple[list[dict]]:
+        if self.schema_checker(gold_list, sys_list) != True:
+            self.logger.error("Please check the column names in your gold and sys files.")
+            raise BaseException
+
+        gold, sys, similarity, gold_matched, sys_matched = [], [], [], [], []
+        similarity_matrix = [self.calc_similarity(si, sys_list) for si in gold_list]
+        best_matches = [
+            (gi, si, similarity_matrix[gi][si])
+            for gi in range(len(similarity_matrix))
+            for si in range(len(similarity_matrix[gi]))
+            if similarity_matrix[gi][si] > self.threshold
+        ]
+        best_matches.sort(key=lambda x: x[2], reverse=True)
+
+        # find the best matches in the similarity matrix
+        for gi, si, sim in best_matches:
+            if gi not in gold_matched and si not in sys_matched:
+                gold.append(gold_list[gi])
+                sys.append(sys_list[si])
+                gold_matched.append(gi)
+                sys_matched.append(si)
+                similarity.append(sim)
+
+        # pad remaining unmatched specific instances
+        for gi in range(len(gold_list)):
+            if gi not in gold_matched:
+                gold.append(gold_list[gi])
+                sys.append(self.create_pad(gold_list[gi]))
+
+        for si in range(len(sys_list)):
+            if si not in sys_matched:
+                sys.append(sys_list[si])
+                gold.append(self.create_pad(sys_list[si]))
+
+        assert len(gold) == len(sys), AssertionError(
+            f"Something went wrong! number of specific instances in gold: {len(gold)}; in sys: {len(sys)}"
+        )
+
+        for ds in [gold, sys]:
+            counter = 0
+            for si in ds:
+                si["Event_ID"] = f"{si['Event_ID']}-{counter}"
+                counter += 1
+
+        return (gold, sys)
diff --git a/Evaluation/weights.py b/Evaluation/weights.py
index 5fc727c85..b76df4ff6 100644
--- a/Evaluation/weights.py
+++ b/Evaluation/weights.py
@@ -112,4 +112,4 @@
         # "Country_Norm": 1,
         # "Location_Norm": 1,
     },
-}
+}
\ No newline at end of file
diff --git a/README.md b/README.md
index 6b8b38017..7f33228fb 100644
--- a/README.md
+++ b/README.md
@@ -36,7 +36,8 @@ If you have generated some LLM output and would like to test it against the dev
 
 Choose a new experiment name! You will use this <EXPERIMENT_NAME> for the whole pipeline.
 
-#### PRESTEPS
+#### PRESTEP (before Step 2):
+If the system output is split across several files (such as Mixtral and Mistral system outputs), then first merge it:
 
 - Normalizing JSON output for Mistral/Mixtral
     If the system output is split across several files (such as Mixtral and Mistral system outputs), then first merge it:
@@ -128,7 +129,7 @@ Also, this config will result in evaluating only on this smaller set of columns,
 ```
 
 
-##### (B) Evaluate
+##### (B) Evaluate main events
  When your config is ready, run the evaluation script:
 
 ```shell
@@ -146,6 +147,37 @@ poetry run python3 Evaluation/evaluator.py --sys-file  Database/output/nlp4clima
 --weights_config nlp4climate
 ```
 
+#### Evaluate sub events (ie. specific instances)
+
+Specific instances can be evaluated using the same script. The same script (`Evaluation/evalutor.py`) will automatically match specific instances from the gold data with the system output. If no match exists for a specific instance, it will be matched up with a "padded" example with NULL values so that the system is penalized for not having been able to find a particular specific instance or for finding extra specific instances not found in the gold dataset.
+
+Below is a scipt that evaluates two dummy sets (gold and sys) to showcase a working example and the correct schema for the `.parquet` files. Sub events are evaluated separately from main events.
+
+```shell
+poetry run python3 Evaluation/evaluator.py \
+--sys-file tests/specific_instance_eval/test_sys_list_death.parquet \
+--gold-file tests/specific_instance_eval/test_gold_list_death.parquet \
+--model-name "specific_instance_eval_test/dev/deaths" \
+--event_type sub \
+--weights_config specific_instance \
+--specific_instance_type deaths
+```
+If run properly, you should see the results in `Database/evaluation_results/specific_instance_eval_test`:
+
+```shell
+Database/evaluation_results/specific_instance_eval_test
+└── dev
+    └── deaths
+        ├── all_27_deaths_avg_per_event_id_results.csv # <- average error rate grouped by event_id
+        ├── all_27_deaths_avg_results.json # <- overall average results
+        ├── all_27_deaths_results.csv # <- results for each pair of gold/sys
+        ├── gold_deaths.parquet # <- modified gold file with matches + padded specific instances
+        └── sys_deaths.parquet # <- modified sys file with matches + padded specific instances
+```
+
+> [!WARNING]
+> Do not commit these files to your branch or to `main`, big thanks!
+
 ### Parsing and normalization
 
 If you have new events to add to the database, first parse them and insert them.
@@ -203,14 +235,6 @@ poetry run python3 Database/gold_from_excel.py --input-file "Database/gold/Impac
 ```
 
 These results are not split to test/dev.
-The plan is to expand this functionality further and evaluate subevents
-
-To be implemented:
-- [ ] How to evaluate subevents when the gold may contain more/less than the system output? Maybe subevents can be matched by location and timestamp and evaluated accordingly -- finding too many could be penalized.
-- [ ] Match the short uuids (generated by [Database/scr/normalize_utils.pyrandom_short_uuid](Database/scr/normalize_utils.pyrandom_short_uuid)) in the excel sheet for the ones that already exist in the dev and test sets.
-- [ ] Make any edits (if needed) to the evaluation script so it can handle subevents
-
-(Input appreciated! Just email @i-be-snek)
 
 > [!IMPORTANT]
 > Please don't track or push excel sheets into the repository
diff --git a/poetry.lock b/poetry.lock
index 5dc114869..27840d287 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -871,6 +871,40 @@ dev-test = ["coverage", "pytest (>=3.10)", "pytest-asyncio (>=0.17)", "sphinx (<
 requests = ["requests (>=2.16.2)", "urllib3 (>=1.24.2)"]
 timezone = ["pytz"]
 
+[[package]]
+name = "huggingface-hub"
+version = "0.24.0"
+description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
+optional = false
+python-versions = ">=3.8.0"
+files = [
+    {file = "huggingface_hub-0.24.0-py3-none-any.whl", hash = "sha256:7ad92edefb93d8145c061f6df8d99df2ff85f8379ba5fac8a95aca0642afa5d7"},
+    {file = "huggingface_hub-0.24.0.tar.gz", hash = "sha256:6c7092736b577d89d57b3cdfea026f1b0dc2234ae783fa0d59caf1bf7d52dfa7"},
+]
+
+[package.dependencies]
+filelock = "*"
+fsspec = ">=2023.5.0"
+packaging = ">=20.9"
+pyyaml = ">=5.1"
+requests = "*"
+tqdm = ">=4.42.1"
+typing-extensions = ">=3.7.4.3"
+
+[package.extras]
+all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio", "jedi", "minijinja (>=1.0)", "mypy (==1.5.1)", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.5.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"]
+cli = ["InquirerPy (==0.3.4)"]
+dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio", "jedi", "minijinja (>=1.0)", "mypy (==1.5.1)", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.5.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"]
+fastai = ["fastai (>=2.4)", "fastcore (>=1.3.27)", "toml"]
+hf-transfer = ["hf-transfer (>=0.1.4)"]
+inference = ["aiohttp", "minijinja (>=1.0)"]
+quality = ["mypy (==1.5.1)", "ruff (>=0.5.0)"]
+tensorflow = ["graphviz", "pydot", "tensorflow"]
+tensorflow-testing = ["keras (<3.0)", "tensorflow"]
+testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio", "jedi", "minijinja (>=1.0)", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "soundfile", "urllib3 (<2.0)"]
+torch = ["safetensors[torch]", "torch"]
+typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)"]
+
 [[package]]
 name = "identify"
 version = "2.5.36"
@@ -915,6 +949,31 @@ docs = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.link
 perf = ["ipython"]
 testing = ["flufl.flake8", "importlib-resources (>=1.3)", "jaraco.test (>=5.4)", "packaging", "pyfakefs", "pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-perf (>=0.9.2)", "pytest-ruff (>=0.2.1)"]
 
+[[package]]
+name = "iniconfig"
+version = "2.0.0"
+description = "brain-dead simple config-ini parsing"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "iniconfig-2.0.0-py3-none-any.whl", hash = "sha256:b6a85871a79d2e3b22d2d1b94ac2824226a63c6b741c88f7ae975f18b6778374"},
+    {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"},
+]
+
+[[package]]
+name = "intel-openmp"
+version = "2021.4.0"
+description = "Intel OpenMP* Runtime Library"
+optional = false
+python-versions = "*"
+files = [
+    {file = "intel_openmp-2021.4.0-py2.py3-none-macosx_10_15_x86_64.macosx_11_0_x86_64.whl", hash = "sha256:41c01e266a7fdb631a7609191709322da2bbf24b252ba763f125dd651bcc7675"},
+    {file = "intel_openmp-2021.4.0-py2.py3-none-manylinux1_i686.whl", hash = "sha256:3b921236a38384e2016f0f3d65af6732cf2c12918087128a9163225451e776f2"},
+    {file = "intel_openmp-2021.4.0-py2.py3-none-manylinux1_x86_64.whl", hash = "sha256:e2240ab8d01472fed04f3544a878cda5da16c26232b7ea1b59132dbfb48b186e"},
+    {file = "intel_openmp-2021.4.0-py2.py3-none-win32.whl", hash = "sha256:6e863d8fd3d7e8ef389d52cf97a50fe2afe1a19247e8c0d168ce021546f96fc9"},
+    {file = "intel_openmp-2021.4.0-py2.py3-none-win_amd64.whl", hash = "sha256:eef4c8bcc8acefd7f5cd3b9384dbf73d59e2c99fc56545712ded913f43c4a94f"},
+]
+
 [[package]]
 name = "ipykernel"
 version = "6.29.4"
@@ -1288,6 +1347,41 @@ files = [
 [package.dependencies]
 traitlets = "*"
 
+[[package]]
+name = "mkl"
+version = "2021.4.0"
+description = "Intel® oneAPI Math Kernel Library"
+optional = false
+python-versions = "*"
+files = [
+    {file = "mkl-2021.4.0-py2.py3-none-macosx_10_15_x86_64.macosx_11_0_x86_64.whl", hash = "sha256:67460f5cd7e30e405b54d70d1ed3ca78118370b65f7327d495e9c8847705e2fb"},
+    {file = "mkl-2021.4.0-py2.py3-none-manylinux1_i686.whl", hash = "sha256:636d07d90e68ccc9630c654d47ce9fdeb036bb46e2b193b3a9ac8cfea683cce5"},
+    {file = "mkl-2021.4.0-py2.py3-none-manylinux1_x86_64.whl", hash = "sha256:398dbf2b0d12acaf54117a5210e8f191827f373d362d796091d161f610c1ebfb"},
+    {file = "mkl-2021.4.0-py2.py3-none-win32.whl", hash = "sha256:439c640b269a5668134e3dcbcea4350459c4a8bc46469669b2d67e07e3d330e8"},
+    {file = "mkl-2021.4.0-py2.py3-none-win_amd64.whl", hash = "sha256:ceef3cafce4c009dd25f65d7ad0d833a0fbadc3d8903991ec92351fe5de1e718"},
+]
+
+[package.dependencies]
+intel-openmp = "==2021.*"
+tbb = "==2021.*"
+
+[[package]]
+name = "mpmath"
+version = "1.3.0"
+description = "Python library for arbitrary-precision floating-point arithmetic"
+optional = false
+python-versions = "*"
+files = [
+    {file = "mpmath-1.3.0-py3-none-any.whl", hash = "sha256:a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c"},
+    {file = "mpmath-1.3.0.tar.gz", hash = "sha256:7a28eb2a9774d00c7bc92411c19a89209d5da7c4c9a9e227be8330a23a25b91f"},
+]
+
+[package.extras]
+develop = ["codecov", "pycodestyle", "pytest (>=4.6)", "pytest-cov", "wheel"]
+docs = ["sphinx"]
+gmpy = ["gmpy2 (>=2.1.0a4)"]
+tests = ["pytest (>=4.6)"]
+
 [[package]]
 name = "murmurhash"
 version = "1.0.10"
@@ -1341,6 +1435,24 @@ files = [
     {file = "nest_asyncio-1.6.0.tar.gz", hash = "sha256:6f172d5449aca15afd6c646851f4e31e02c598d553a667e38cafa997cfec55fe"},
 ]
 
+[[package]]
+name = "networkx"
+version = "3.1"
+description = "Python package for creating and manipulating graphs and networks"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "networkx-3.1-py3-none-any.whl", hash = "sha256:4f33f68cb2afcf86f28a45f43efc27a9386b535d567d2127f8f61d51dec58d36"},
+    {file = "networkx-3.1.tar.gz", hash = "sha256:de346335408f84de0eada6ff9fafafff9bcda11f0a0dfaa931133debb146ab61"},
+]
+
+[package.extras]
+default = ["matplotlib (>=3.4)", "numpy (>=1.20)", "pandas (>=1.3)", "scipy (>=1.8)"]
+developer = ["mypy (>=1.1)", "pre-commit (>=3.2)"]
+doc = ["nb2plots (>=0.6)", "numpydoc (>=1.5)", "pillow (>=9.4)", "pydata-sphinx-theme (>=0.13)", "sphinx (>=6.1)", "sphinx-gallery (>=0.12)", "texext (>=0.6.7)"]
+extra = ["lxml (>=4.6)", "pydot (>=1.4.2)", "pygraphviz (>=1.10)", "sympy (>=1.10)"]
+test = ["codecov (>=2.1)", "pytest (>=7.2)", "pytest-cov (>=4.0)"]
+
 [[package]]
 name = "nodeenv"
 version = "1.8.0"
@@ -1419,6 +1531,148 @@ files = [
     {file = "numpy-1.24.0.tar.gz", hash = "sha256:c4ab7c9711fe6b235e86487ca74c1b092a6dd59a3cb45b63241ea0a148501853"},
 ]
 
+[[package]]
+name = "nvidia-cublas-cu12"
+version = "12.1.3.1"
+description = "CUBLAS native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl", hash = "sha256:ee53ccca76a6fc08fb9701aa95b6ceb242cdaab118c3bb152af4e579af792728"},
+    {file = "nvidia_cublas_cu12-12.1.3.1-py3-none-win_amd64.whl", hash = "sha256:2b964d60e8cf11b5e1073d179d85fa340c120e99b3067558f3cf98dd69d02906"},
+]
+
+[[package]]
+name = "nvidia-cuda-cupti-cu12"
+version = "12.1.105"
+description = "CUDA profiling tools runtime libs."
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:e54fde3983165c624cb79254ae9818a456eb6e87a7fd4d56a2352c24ee542d7e"},
+    {file = "nvidia_cuda_cupti_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:bea8236d13a0ac7190bd2919c3e8e6ce1e402104276e6f9694479e48bb0eb2a4"},
+]
+
+[[package]]
+name = "nvidia-cuda-nvrtc-cu12"
+version = "12.1.105"
+description = "NVRTC native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:339b385f50c309763ca65456ec75e17bbefcbbf2893f462cb8b90584cd27a1c2"},
+    {file = "nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:0a98a522d9ff138b96c010a65e145dc1b4850e9ecb75a0172371793752fd46ed"},
+]
+
+[[package]]
+name = "nvidia-cuda-runtime-cu12"
+version = "12.1.105"
+description = "CUDA Runtime native Libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:6e258468ddf5796e25f1dc591a31029fa317d97a0a94ed93468fc86301d61e40"},
+    {file = "nvidia_cuda_runtime_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:dfb46ef84d73fababab44cf03e3b83f80700d27ca300e537f85f636fac474344"},
+]
+
+[[package]]
+name = "nvidia-cudnn-cu12"
+version = "8.9.2.26"
+description = "cuDNN runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl", hash = "sha256:5ccb288774fdfb07a7e7025ffec286971c06d8d7b4fb162525334616d7629ff9"},
+]
+
+[package.dependencies]
+nvidia-cublas-cu12 = "*"
+
+[[package]]
+name = "nvidia-cufft-cu12"
+version = "11.0.2.54"
+description = "CUFFT native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl", hash = "sha256:794e3948a1aa71fd817c3775866943936774d1c14e7628c74f6f7417224cdf56"},
+    {file = "nvidia_cufft_cu12-11.0.2.54-py3-none-win_amd64.whl", hash = "sha256:d9ac353f78ff89951da4af698f80870b1534ed69993f10a4cf1d96f21357e253"},
+]
+
+[[package]]
+name = "nvidia-curand-cu12"
+version = "10.3.2.106"
+description = "CURAND native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:9d264c5036dde4e64f1de8c50ae753237c12e0b1348738169cd0f8a536c0e1e0"},
+    {file = "nvidia_curand_cu12-10.3.2.106-py3-none-win_amd64.whl", hash = "sha256:75b6b0c574c0037839121317e17fd01f8a69fd2ef8e25853d826fec30bdba74a"},
+]
+
+[[package]]
+name = "nvidia-cusolver-cu12"
+version = "11.4.5.107"
+description = "CUDA solver native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl", hash = "sha256:8a7ec542f0412294b15072fa7dab71d31334014a69f953004ea7a118206fe0dd"},
+    {file = "nvidia_cusolver_cu12-11.4.5.107-py3-none-win_amd64.whl", hash = "sha256:74e0c3a24c78612192a74fcd90dd117f1cf21dea4822e66d89e8ea80e3cd2da5"},
+]
+
+[package.dependencies]
+nvidia-cublas-cu12 = "*"
+nvidia-cusparse-cu12 = "*"
+nvidia-nvjitlink-cu12 = "*"
+
+[[package]]
+name = "nvidia-cusparse-cu12"
+version = "12.1.0.106"
+description = "CUSPARSE native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:f3b50f42cf363f86ab21f720998517a659a48131e8d538dc02f8768237bd884c"},
+    {file = "nvidia_cusparse_cu12-12.1.0.106-py3-none-win_amd64.whl", hash = "sha256:b798237e81b9719373e8fae8d4f091b70a0cf09d9d85c95a557e11df2d8e9a5a"},
+]
+
+[package.dependencies]
+nvidia-nvjitlink-cu12 = "*"
+
+[[package]]
+name = "nvidia-nccl-cu12"
+version = "2.20.5"
+description = "NVIDIA Collective Communication Library (NCCL) Runtime"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_aarch64.whl", hash = "sha256:1fc150d5c3250b170b29410ba682384b14581db722b2531b0d8d33c595f33d01"},
+    {file = "nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl", hash = "sha256:057f6bf9685f75215d0c53bf3ac4a10b3e6578351de307abad9e18a99182af56"},
+]
+
+[[package]]
+name = "nvidia-nvjitlink-cu12"
+version = "12.5.82"
+description = "Nvidia JIT LTO Library"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_nvjitlink_cu12-12.5.82-py3-none-manylinux2014_x86_64.whl", hash = "sha256:f9b37bc5c8cf7509665cb6ada5aaa0ce65618f2332b7d3e78e9790511f111212"},
+    {file = "nvidia_nvjitlink_cu12-12.5.82-py3-none-win_amd64.whl", hash = "sha256:e782564d705ff0bf61ac3e1bf730166da66dd2fe9012f111ede5fc49b64ae697"},
+]
+
+[[package]]
+name = "nvidia-nvtx-cu12"
+version = "12.1.105"
+description = "NVIDIA Tools Extension"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:dc21cf308ca5691e7c04d962e213f8a4aa9bbfa23d95412f452254c2caeb09e5"},
+    {file = "nvidia_nvtx_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:65f4d98982b31b60026e0e6de73fbdfc09d08a96f4656dd3665ca616a11e1e82"},
+]
+
 [[package]]
 name = "openpyxl"
 version = "3.1.2"
@@ -1567,6 +1821,21 @@ docs = ["furo (>=2023.9.10)", "proselint (>=0.13)", "sphinx (>=7.2.6)", "sphinx-
 test = ["appdirs (==1.4.4)", "covdefaults (>=2.3)", "pytest (>=7.4.3)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)"]
 type = ["mypy (>=1.8)"]
 
+[[package]]
+name = "pluggy"
+version = "1.5.0"
+description = "plugin and hook calling mechanisms for python"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "pluggy-1.5.0-py3-none-any.whl", hash = "sha256:44e1ad92c8ca002de6377e165f3e0f1be63266ab4d554740532335b9d75ea669"},
+    {file = "pluggy-1.5.0.tar.gz", hash = "sha256:2cffa88e94fdc978c4c574f15f9e59b7f4201d439195c3715ca9e2486f1d0cf1"},
+]
+
+[package.extras]
+dev = ["pre-commit", "tox"]
+testing = ["pytest", "pytest-benchmark"]
+
 [[package]]
 name = "pre-commit"
 version = "3.5.0"
@@ -1846,6 +2115,28 @@ files = [
 [package.extras]
 windows-terminal = ["colorama (>=0.4.6)"]
 
+[[package]]
+name = "pytest"
+version = "8.2.2"
+description = "pytest: simple powerful testing with Python"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "pytest-8.2.2-py3-none-any.whl", hash = "sha256:c434598117762e2bd304e526244f67bf66bbd7b5d6cf22138be51ff661980343"},
+    {file = "pytest-8.2.2.tar.gz", hash = "sha256:de4bb8104e201939ccdc688b27a89a7be2079b22e2bd2b07f806b6ba71117977"},
+]
+
+[package.dependencies]
+colorama = {version = "*", markers = "sys_platform == \"win32\""}
+exceptiongroup = {version = ">=1.0.0rc8", markers = "python_version < \"3.11\""}
+iniconfig = "*"
+packaging = "*"
+pluggy = ">=1.5,<2.0"
+tomli = {version = ">=1", markers = "python_version < \"3.11\""}
+
+[package.extras]
+dev = ["argcomplete", "attrs (>=19.2)", "hypothesis (>=3.56)", "mock", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"]
+
 [[package]]
 name = "python-dateutil"
 version = "2.9.0.post0"
@@ -2207,6 +2498,128 @@ redis = ["redis (>=3)"]
 security = ["itsdangerous (>=2.0)"]
 yaml = ["pyyaml (>=6.0.1)"]
 
+[[package]]
+name = "safetensors"
+version = "0.4.3"
+description = ""
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "safetensors-0.4.3-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:dcf5705cab159ce0130cd56057f5f3425023c407e170bca60b4868048bae64fd"},
+    {file = "safetensors-0.4.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:bb4f8c5d0358a31e9a08daeebb68f5e161cdd4018855426d3f0c23bb51087055"},
+    {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:70a5319ef409e7f88686a46607cbc3c428271069d8b770076feaf913664a07ac"},
+    {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:fb9c65bd82f9ef3ce4970dc19ee86be5f6f93d032159acf35e663c6bea02b237"},
+    {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:edb5698a7bc282089f64c96c477846950358a46ede85a1c040e0230344fdde10"},
+    {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:efcc860be094b8d19ac61b452ec635c7acb9afa77beb218b1d7784c6d41fe8ad"},
+    {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d88b33980222085dd6001ae2cad87c6068e0991d4f5ccf44975d216db3b57376"},
+    {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:5fc6775529fb9f0ce2266edd3e5d3f10aab068e49f765e11f6f2a63b5367021d"},
+    {file = "safetensors-0.4.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:9c6ad011c1b4e3acff058d6b090f1da8e55a332fbf84695cf3100c649cc452d1"},
+    {file = "safetensors-0.4.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:8c496c5401c1b9c46d41a7688e8ff5b0310a3b9bae31ce0f0ae870e1ea2b8caf"},
+    {file = "safetensors-0.4.3-cp310-none-win32.whl", hash = "sha256:38e2a8666178224a51cca61d3cb4c88704f696eac8f72a49a598a93bbd8a4af9"},
+    {file = "safetensors-0.4.3-cp310-none-win_amd64.whl", hash = "sha256:393e6e391467d1b2b829c77e47d726f3b9b93630e6a045b1d1fca67dc78bf632"},
+    {file = "safetensors-0.4.3-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:22f3b5d65e440cec0de8edaa672efa888030802e11c09b3d6203bff60ebff05a"},
+    {file = "safetensors-0.4.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7c4fa560ebd4522adddb71dcd25d09bf211b5634003f015a4b815b7647d62ebe"},
+    {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e9afd5358719f1b2cf425fad638fc3c887997d6782da317096877e5b15b2ce93"},
+    {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d8c5093206ef4b198600ae484230402af6713dab1bd5b8e231905d754022bec7"},
+    {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e0b2104df1579d6ba9052c0ae0e3137c9698b2d85b0645507e6fd1813b70931a"},
+    {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8cf18888606dad030455d18f6c381720e57fc6a4170ee1966adb7ebc98d4d6a3"},
+    {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0bf4f9d6323d9f86eef5567eabd88f070691cf031d4c0df27a40d3b4aaee755b"},
+    {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:585c9ae13a205807b63bef8a37994f30c917ff800ab8a1ca9c9b5d73024f97ee"},
+    {file = "safetensors-0.4.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:faefeb3b81bdfb4e5a55b9bbdf3d8d8753f65506e1d67d03f5c851a6c87150e9"},
+    {file = "safetensors-0.4.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:befdf0167ad626f22f6aac6163477fcefa342224a22f11fdd05abb3995c1783c"},
+    {file = "safetensors-0.4.3-cp311-none-win32.whl", hash = "sha256:a7cef55929dcbef24af3eb40bedec35d82c3c2fa46338bb13ecf3c5720af8a61"},
+    {file = "safetensors-0.4.3-cp311-none-win_amd64.whl", hash = "sha256:840b7ac0eff5633e1d053cc9db12fdf56b566e9403b4950b2dc85393d9b88d67"},
+    {file = "safetensors-0.4.3-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:22d21760dc6ebae42e9c058d75aa9907d9f35e38f896e3c69ba0e7b213033856"},
+    {file = "safetensors-0.4.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:8d22c1a10dff3f64d0d68abb8298a3fd88ccff79f408a3e15b3e7f637ef5c980"},
+    {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b1648568667f820b8c48317c7006221dc40aced1869908c187f493838a1362bc"},
+    {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:446e9fe52c051aeab12aac63d1017e0f68a02a92a027b901c4f8e931b24e5397"},
+    {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:fef5d70683643618244a4f5221053567ca3e77c2531e42ad48ae05fae909f542"},
+    {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2a1f4430cc0c9d6afa01214a4b3919d0a029637df8e09675ceef1ca3f0dfa0df"},
+    {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2d603846a8585b9432a0fd415db1d4c57c0f860eb4aea21f92559ff9902bae4d"},
+    {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:a844cdb5d7cbc22f5f16c7e2a0271170750763c4db08381b7f696dbd2c78a361"},
+    {file = "safetensors-0.4.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:88887f69f7a00cf02b954cdc3034ffb383b2303bc0ab481d4716e2da51ddc10e"},
+    {file = "safetensors-0.4.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:ee463219d9ec6c2be1d331ab13a8e0cd50d2f32240a81d498266d77d07b7e71e"},
+    {file = "safetensors-0.4.3-cp312-none-win32.whl", hash = "sha256:d0dd4a1db09db2dba0f94d15addc7e7cd3a7b0d393aa4c7518c39ae7374623c3"},
+    {file = "safetensors-0.4.3-cp312-none-win_amd64.whl", hash = "sha256:d14d30c25897b2bf19b6fb5ff7e26cc40006ad53fd4a88244fdf26517d852dd7"},
+    {file = "safetensors-0.4.3-cp37-cp37m-macosx_10_12_x86_64.whl", hash = "sha256:d1456f814655b224d4bf6e7915c51ce74e389b413be791203092b7ff78c936dd"},
+    {file = "safetensors-0.4.3-cp37-cp37m-macosx_11_0_arm64.whl", hash = "sha256:455d538aa1aae4a8b279344a08136d3f16334247907b18a5c3c7fa88ef0d3c46"},
+    {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cf476bca34e1340ee3294ef13e2c625833f83d096cfdf69a5342475602004f95"},
+    {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:02ef3a24face643456020536591fbd3c717c5abaa2737ec428ccbbc86dffa7a4"},
+    {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7de32d0d34b6623bb56ca278f90db081f85fb9c5d327e3c18fd23ac64f465768"},
+    {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2a0deb16a1d3ea90c244ceb42d2c6c276059616be21a19ac7101aa97da448faf"},
+    {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c59d51f182c729f47e841510b70b967b0752039f79f1de23bcdd86462a9b09ee"},
+    {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:1f598b713cc1a4eb31d3b3203557ac308acf21c8f41104cdd74bf640c6e538e3"},
+    {file = "safetensors-0.4.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:5757e4688f20df083e233b47de43845d1adb7e17b6cf7da5f8444416fc53828d"},
+    {file = "safetensors-0.4.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:fe746d03ed8d193674a26105e4f0fe6c726f5bb602ffc695b409eaf02f04763d"},
+    {file = "safetensors-0.4.3-cp37-none-win32.whl", hash = "sha256:0d5ffc6a80f715c30af253e0e288ad1cd97a3d0086c9c87995e5093ebc075e50"},
+    {file = "safetensors-0.4.3-cp37-none-win_amd64.whl", hash = "sha256:a11c374eb63a9c16c5ed146457241182f310902bd2a9c18255781bb832b6748b"},
+    {file = "safetensors-0.4.3-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:b1e31be7945f66be23f4ec1682bb47faa3df34cb89fc68527de6554d3c4258a4"},
+    {file = "safetensors-0.4.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:03a4447c784917c9bf01d8f2ac5080bc15c41692202cd5f406afba16629e84d6"},
+    {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d244bcafeb1bc06d47cfee71727e775bca88a8efda77a13e7306aae3813fa7e4"},
+    {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:53c4879b9c6bd7cd25d114ee0ef95420e2812e676314300624594940a8d6a91f"},
+    {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:74707624b81f1b7f2b93f5619d4a9f00934d5948005a03f2c1845ffbfff42212"},
+    {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0d52c958dc210265157573f81d34adf54e255bc2b59ded6218500c9b15a750eb"},
+    {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6f9568f380f513a60139971169c4a358b8731509cc19112369902eddb33faa4d"},
+    {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:0d9cd8e1560dfc514b6d7859247dc6a86ad2f83151a62c577428d5102d872721"},
+    {file = "safetensors-0.4.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:89f9f17b0dacb913ed87d57afbc8aad85ea42c1085bd5de2f20d83d13e9fc4b2"},
+    {file = "safetensors-0.4.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:1139eb436fd201c133d03c81209d39ac57e129f5e74e34bb9ab60f8d9b726270"},
+    {file = "safetensors-0.4.3-cp38-none-win32.whl", hash = "sha256:d9c289f140a9ae4853fc2236a2ffc9a9f2d5eae0cb673167e0f1b8c18c0961ac"},
+    {file = "safetensors-0.4.3-cp38-none-win_amd64.whl", hash = "sha256:622afd28968ef3e9786562d352659a37de4481a4070f4ebac883f98c5836563e"},
+    {file = "safetensors-0.4.3-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:8651c7299cbd8b4161a36cd6a322fa07d39cd23535b144d02f1c1972d0c62f3c"},
+    {file = "safetensors-0.4.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e375d975159ac534c7161269de24ddcd490df2157b55c1a6eeace6cbb56903f0"},
+    {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:084fc436e317f83f7071fc6a62ca1c513b2103db325cd09952914b50f51cf78f"},
+    {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:41a727a7f5e6ad9f1db6951adee21bbdadc632363d79dc434876369a17de6ad6"},
+    {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e7dbbde64b6c534548696808a0e01276d28ea5773bc9a2dfb97a88cd3dffe3df"},
+    {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:bbae3b4b9d997971431c346edbfe6e41e98424a097860ee872721e176040a893"},
+    {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:01e4b22e3284cd866edeabe4f4d896229495da457229408d2e1e4810c5187121"},
+    {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:0dd37306546b58d3043eb044c8103a02792cc024b51d1dd16bd3dd1f334cb3ed"},
+    {file = "safetensors-0.4.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:d8815b5e1dac85fc534a97fd339e12404db557878c090f90442247e87c8aeaea"},
+    {file = "safetensors-0.4.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:e011cc162503c19f4b1fd63dfcddf73739c7a243a17dac09b78e57a00983ab35"},
+    {file = "safetensors-0.4.3-cp39-none-win32.whl", hash = "sha256:01feb3089e5932d7e662eda77c3ecc389f97c0883c4a12b5cfdc32b589a811c3"},
+    {file = "safetensors-0.4.3-cp39-none-win_amd64.whl", hash = "sha256:3f9cdca09052f585e62328c1c2923c70f46814715c795be65f0b93f57ec98a02"},
+    {file = "safetensors-0.4.3-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:1b89381517891a7bb7d1405d828b2bf5d75528299f8231e9346b8eba092227f9"},
+    {file = "safetensors-0.4.3-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:cd6fff9e56df398abc5866b19a32124815b656613c1c5ec0f9350906fd798aac"},
+    {file = "safetensors-0.4.3-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:840caf38d86aa7014fe37ade5d0d84e23dcfbc798b8078015831996ecbc206a3"},
+    {file = "safetensors-0.4.3-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f9650713b2cfa9537a2baf7dd9fee458b24a0aaaa6cafcea8bdd5fb2b8efdc34"},
+    {file = "safetensors-0.4.3-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e4119532cd10dba04b423e0f86aecb96cfa5a602238c0aa012f70c3a40c44b50"},
+    {file = "safetensors-0.4.3-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:e066e8861eef6387b7c772344d1fe1f9a72800e04ee9a54239d460c400c72aab"},
+    {file = "safetensors-0.4.3-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:90964917f5b0fa0fa07e9a051fbef100250c04d150b7026ccbf87a34a54012e0"},
+    {file = "safetensors-0.4.3-pp37-pypy37_pp73-macosx_10_12_x86_64.whl", hash = "sha256:c41e1893d1206aa7054029681778d9a58b3529d4c807002c156d58426c225173"},
+    {file = "safetensors-0.4.3-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ae7613a119a71a497d012ccc83775c308b9c1dab454806291427f84397d852fd"},
+    {file = "safetensors-0.4.3-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4f9bac020faba7f5dc481e881b14b6425265feabb5bfc552551d21189c0eddc3"},
+    {file = "safetensors-0.4.3-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:420a98f593ff9930f5822560d14c395ccbc57342ddff3b463bc0b3d6b1951550"},
+    {file = "safetensors-0.4.3-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:f5e6883af9a68c0028f70a4c19d5a6ab6238a379be36ad300a22318316c00cb0"},
+    {file = "safetensors-0.4.3-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:cdd0a3b5da66e7f377474599814dbf5cbf135ff059cc73694de129b58a5e8a2c"},
+    {file = "safetensors-0.4.3-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:9bfb92f82574d9e58401d79c70c716985dc049b635fef6eecbb024c79b2c46ad"},
+    {file = "safetensors-0.4.3-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:3615a96dd2dcc30eb66d82bc76cda2565f4f7bfa89fcb0e31ba3cea8a1a9ecbb"},
+    {file = "safetensors-0.4.3-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:868ad1b6fc41209ab6bd12f63923e8baeb1a086814cb2e81a65ed3d497e0cf8f"},
+    {file = "safetensors-0.4.3-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b7ffba80aa49bd09195145a7fd233a7781173b422eeb995096f2b30591639517"},
+    {file = "safetensors-0.4.3-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:c0acbe31340ab150423347e5b9cc595867d814244ac14218932a5cf1dd38eb39"},
+    {file = "safetensors-0.4.3-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:19bbdf95de2cf64f25cd614c5236c8b06eb2cfa47cbf64311f4b5d80224623a3"},
+    {file = "safetensors-0.4.3-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:b852e47eb08475c2c1bd8131207b405793bfc20d6f45aff893d3baaad449ed14"},
+    {file = "safetensors-0.4.3-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:5d07cbca5b99babb692d76d8151bec46f461f8ad8daafbfd96b2fca40cadae65"},
+    {file = "safetensors-0.4.3-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:1ab6527a20586d94291c96e00a668fa03f86189b8a9defa2cdd34a1a01acc7d5"},
+    {file = "safetensors-0.4.3-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:02318f01e332cc23ffb4f6716e05a492c5f18b1d13e343c49265149396284a44"},
+    {file = "safetensors-0.4.3-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ec4b52ce9a396260eb9731eb6aea41a7320de22ed73a1042c2230af0212758ce"},
+    {file = "safetensors-0.4.3-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:018b691383026a2436a22b648873ed11444a364324e7088b99cd2503dd828400"},
+    {file = "safetensors-0.4.3-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:309b10dbcab63269ecbf0e2ca10ce59223bb756ca5d431ce9c9eeabd446569da"},
+    {file = "safetensors-0.4.3-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:b277482120df46e27a58082df06a15aebda4481e30a1c21eefd0921ae7e03f65"},
+    {file = "safetensors-0.4.3.tar.gz", hash = "sha256:2f85fc50c4e07a21e95c24e07460fe6f7e2859d0ce88092838352b798ce711c2"},
+]
+
+[package.extras]
+all = ["safetensors[jax]", "safetensors[numpy]", "safetensors[paddlepaddle]", "safetensors[pinned-tf]", "safetensors[quality]", "safetensors[testing]", "safetensors[torch]"]
+dev = ["safetensors[all]"]
+jax = ["flax (>=0.6.3)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "safetensors[numpy]"]
+mlx = ["mlx (>=0.0.9)"]
+numpy = ["numpy (>=1.21.6)"]
+paddlepaddle = ["paddlepaddle (>=2.4.1)", "safetensors[numpy]"]
+pinned-tf = ["safetensors[numpy]", "tensorflow (==2.11.0)"]
+quality = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "isort (>=5.5.4)"]
+tensorflow = ["safetensors[numpy]", "tensorflow (>=2.11.0)"]
+testing = ["h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "hypothesis (>=6.70.2)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "safetensors[numpy]", "setuptools-rust (>=1.5.2)"]
+torch = ["safetensors[numpy]", "torch (>=1.10)"]
+
 [[package]]
 name = "setuptools"
 version = "69.5.1"
@@ -2268,41 +2681,41 @@ webhdfs = ["requests"]
 
 [[package]]
 name = "spacy"
-version = "3.7.4"
+version = "3.7.5"
 description = "Industrial-strength Natural Language Processing (NLP) in Python"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "spacy-3.7.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:0f748625192f573c07ddea5fcd324919dbfbf4f4a2f7a1fc731e6dcba7321ea1"},
-    {file = "spacy-3.7.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:6288dca7b3a5489b3d7ce68404bc432ca22f826c662a12af47ef7bdb264307fb"},
-    {file = "spacy-3.7.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ef59db99b12a72d2646be3888d87f94c59e11cd07adc2f50a8130e83f07eb1cf"},
-    {file = "spacy-3.7.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f07477a4027711c22b3865e78dc9076335c03fcf318a6736159bf07e2a923125"},
-    {file = "spacy-3.7.4-cp310-cp310-win_amd64.whl", hash = "sha256:787ce42a837f7edfbd4185356eea893a81b7dd75743d0047f2b9bf179775f970"},
-    {file = "spacy-3.7.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:e82b9da21853d4aee46811804dc7e136895f087fda25c7585172d95eb9b70833"},
-    {file = "spacy-3.7.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:07ffedf51899441070fb70432f8f873696f39e0e31c9ce7403101c459f8a1281"},
-    {file = "spacy-3.7.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ba57bcc111eca7b086ee33a9636df775cfd4b14302f7d0ffbc11e95ac0fb3f0e"},
-    {file = "spacy-3.7.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7580d1565f4d1ccbee9a18531f993a5b9b37ced96f145153dd4e98ceec607a55"},
-    {file = "spacy-3.7.4-cp311-cp311-win_amd64.whl", hash = "sha256:df99c6f0085b1ec8e88beb5fd96d4371cef6fc19c202c41fc4fadc2afd55a157"},
-    {file = "spacy-3.7.4-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b982ebab417189346acb4722637c573830d62e157ba336c3eb6c417249344be1"},
-    {file = "spacy-3.7.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:e7c29e152d8ea060af60da9410fa8ef038f3c9068a206905ee5c704de78f6e87"},
-    {file = "spacy-3.7.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:023c9a008328f55c4717c56c4f8a28073b9961547f7d38a9405c967a52e66d59"},
-    {file = "spacy-3.7.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d1969d3d0fd0c811b7485438460f0ae8cfe16d46b54bcb8d1c26e70914e67e3d"},
-    {file = "spacy-3.7.4-cp312-cp312-win_amd64.whl", hash = "sha256:040f7df5096c817450820eaaa426d54ed266254d16974e9a707a32f5b0f139ae"},
-    {file = "spacy-3.7.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:a6757e8fbfd35dc0ed830296d5756f46d5b8d4b0353925dbe2f9aa33b82c5308"},
-    {file = "spacy-3.7.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c500c1bad9e0488814a75077089aeef64a6b520ae8131578f266a08168106fa3"},
-    {file = "spacy-3.7.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c992e2c5c0cd06c7f3e74fe8d758885117090013931c7938277d1421660bf71f"},
-    {file = "spacy-3.7.4-cp37-cp37m-win_amd64.whl", hash = "sha256:2463c56ab1378f2b9a675340a2e3dfb618989d0da8cdce06429bc9b1dad4f294"},
-    {file = "spacy-3.7.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:b43e92edfa99f34dbb9dd30175f41158d20945e3179055d0071fee19394add96"},
-    {file = "spacy-3.7.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:c26a81d33c93e4a8e3360d61dcce0802fb886de79f666a487ea5abbd3ce4b30b"},
-    {file = "spacy-3.7.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5d7910ca7a91bf423febd8a9a10ca6a4cfcb5c99abdec79df1eb7b67ea3e3c90"},
-    {file = "spacy-3.7.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4b16768b9e5c350b8a383a6bd84cd0481ccdf10ae6231f568598890638065f69"},
-    {file = "spacy-3.7.4-cp38-cp38-win_amd64.whl", hash = "sha256:ed99fb176979b1e3cf6830161f8e881beae54e80147b05fca31d9a67cb12fbca"},
-    {file = "spacy-3.7.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:ca8112330982dbeef125cc5eb40e0349493055835a0ebe29028a0953a25d8522"},
-    {file = "spacy-3.7.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:977f37493d7cf0b5dca155f0450d47890378703283c29919cdcc220db994a775"},
-    {file = "spacy-3.7.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3ad5e931c294d100ec3edb40e40f2722ef505cea16312839dd6467e81d665740"},
-    {file = "spacy-3.7.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:11ebf6054cd3ec3638801d7ff9b709e32fb9c15512b347b489bfe2ccb1102c9f"},
-    {file = "spacy-3.7.4-cp39-cp39-win_amd64.whl", hash = "sha256:f5b930753027ac599f70bb7e77d6a2256191fe582e6f3f0cd624d88f6c279fa4"},
-    {file = "spacy-3.7.4.tar.gz", hash = "sha256:525f2ced2e40761562c8cace93ef6a1e6e8c483f27bd564bc1b15f608efbe85b"},
+    {file = "spacy-3.7.5-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8002897701429ee2ab5ff6921ae43560f4cd17184cb1e10dad761901c12dcb85"},
+    {file = "spacy-3.7.5-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:43acd19efc845e9126b61a05ed7508a0aff509e96e15563f30f810c19e636b7c"},
+    {file = "spacy-3.7.5-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f044522b1271ea54718dc43b6f593b5dad349cd31b3827764c501529b599e09a"},
+    {file = "spacy-3.7.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6a7dbfbca42c1c128fefa6832631fe49e11c850e963af99229f14e2d0ae94f34"},
+    {file = "spacy-3.7.5-cp310-cp310-win_amd64.whl", hash = "sha256:2a21b2a1e1e5d10d15c6f75990b7341d0fc9b454083dfd4222fdd75b9164831c"},
+    {file = "spacy-3.7.5-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:cd93c34bf2a02bbed7df73d42aed8df5e3eb9688c4ea84ec576f740ba939cce5"},
+    {file = "spacy-3.7.5-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:190ba0032a5efdb138487c587c0ebb7a98f86adb917f464b252ee8766b8eec4a"},
+    {file = "spacy-3.7.5-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:38de1c9bbb73b8cdfea2dd6e57450f093c1a1af47515870c1c8640b85b35ab16"},
+    {file = "spacy-3.7.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3dad4853950a2fe6c7a0bdfd791a762d1f8cedd2915c4ae41b2e0ca3a850eefc"},
+    {file = "spacy-3.7.5-cp311-cp311-win_amd64.whl", hash = "sha256:4e00d076871af784c2e43185a71ee676b58893853a05c5b81717b8af2b666c07"},
+    {file = "spacy-3.7.5-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:bf54c3c2425428b328b53a65913d47eb4cb27a1429aa4e8ed979ffc97d4663e0"},
+    {file = "spacy-3.7.5-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:4145cea7f9814fa7d86b2028c2dd83e02f13f80d5ac604a400b2f7d7b26a0e8c"},
+    {file = "spacy-3.7.5-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:262f8ebb71f7ed5ffe8e4f384b2594b7a296be50241ce9fbd9277b5da2f46f38"},
+    {file = "spacy-3.7.5-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:faa1e2b6234ae33c0b1f8dfa5a8dcb66fb891f19231725dfcff4b2666125c250"},
+    {file = "spacy-3.7.5-cp312-cp312-win_amd64.whl", hash = "sha256:07677e270a6d729453cc04b5e2247a96a86320b8845e6428d9f90f217eff0f56"},
+    {file = "spacy-3.7.5-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:3e207dda0639818e2ef8f12e3df82a526de118cc09082b0eee3053ebcd9f8332"},
+    {file = "spacy-3.7.5-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5694dd3b2f6414c18e2a3f31111cd41ffd597e1d614b51c5779f85ff07f08f6c"},
+    {file = "spacy-3.7.5-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d211920ff73d68b8febb1d293f10accbd54f2b2228ecd3530548227b750252b1"},
+    {file = "spacy-3.7.5-cp37-cp37m-win_amd64.whl", hash = "sha256:1171bf4d8541c18a83441be01feb6c735ffc02e9308810cd691c8900a6678cd5"},
+    {file = "spacy-3.7.5-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:d9108f67675fb2078ed77cda61fd4cfc197f9256c28d35cfd946dcb080190ddc"},
+    {file = "spacy-3.7.5-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:12fdc01a4391299a47f16915505cc515fd059e71c7239904e216523354eeb9d9"},
+    {file = "spacy-3.7.5-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7f8fbe9f6b9de1bf05d163a9dd88108b8f20b138986e6ed36f960832e3fcab33"},
+    {file = "spacy-3.7.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d244d524ab5a33530ac5c50fc92c9a41da6c3980f452048b9fc29e1ff1bdd03e"},
+    {file = "spacy-3.7.5-cp38-cp38-win_amd64.whl", hash = "sha256:8b493a8b79a7f3754102fa5ef7e2615568a390fec7ea20db49af55e5f0841fcf"},
+    {file = "spacy-3.7.5-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:fdbb667792d6ca93899645774d1db3fccc327088a92072029be1e4bc25d7cf15"},
+    {file = "spacy-3.7.5-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:4cfb85309e11a39681c9d4941aebb95c1f5e2e3b77a61a5451e2c3849da4b92e"},
+    {file = "spacy-3.7.5-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4b0bf1788ca397eef8e67e9c07cfd9287adac438512dd191e6e6ca0f36357201"},
+    {file = "spacy-3.7.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:591d90d8504e9bd5be5b482be7c6d6a974afbaeb62c3181e966f4e407e0ab300"},
+    {file = "spacy-3.7.5-cp39-cp39-win_amd64.whl", hash = "sha256:713b56fe008c79df01617f3602a0b7e523292211337eb999bdffb910ea1f4825"},
+    {file = "spacy-3.7.5.tar.gz", hash = "sha256:a648c6cbf2acc7a55a69ee9e7fa4f22bdf69aa828a587a1bc5cfff08cf3c2dd3"},
 ]
 
 [package.dependencies]
@@ -2320,15 +2733,15 @@ preshed = ">=3.0.2,<3.1.0"
 pydantic = ">=1.7.4,<1.8 || >1.8,<1.8.1 || >1.8.1,<3.0.0"
 requests = ">=2.13.0,<3.0.0"
 setuptools = "*"
-smart-open = ">=5.2.1,<7.0.0"
 spacy-legacy = ">=3.0.11,<3.1.0"
 spacy-loggers = ">=1.0.0,<2.0.0"
+spacy-transformers = {version = ">=1.1.2,<1.4.0", optional = true, markers = "extra == \"transformers\""}
 srsly = ">=2.4.3,<3.0.0"
 thinc = ">=8.2.2,<8.3.0"
 tqdm = ">=4.38.0,<5.0.0"
-typer = ">=0.3.0,<0.10.0"
+typer = ">=0.3.0,<1.0.0"
 wasabi = ">=0.9.1,<1.2.0"
-weasel = ">=0.1.0,<0.4.0"
+weasel = ">=0.1.0,<0.5.0"
 
 [package.extras]
 apple = ["thinc-apple-ops (>=0.1.0.dev0,<1.0.0)"]
@@ -2357,6 +2770,45 @@ lookups = ["spacy-lookups-data (>=1.0.3,<1.1.0)"]
 th = ["pythainlp (>=2.0)"]
 transformers = ["spacy-transformers (>=1.1.2,<1.4.0)"]
 
+[[package]]
+name = "spacy-alignments"
+version = "0.9.1"
+description = "A spaCy package for the Rust tokenizations library"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "spacy-alignments-0.9.1.tar.gz", hash = "sha256:7e020ec4797d6179060818d01cdb4e0013a52dba544b9bbfb5efcff8851926dc"},
+    {file = "spacy_alignments-0.9.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:f2d9b8da21d7924f4b5e6cfd89234b27f7939c4211c0fa866b3dde4110b96dd6"},
+    {file = "spacy_alignments-0.9.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:12402e2eea5c4b21b197c43c9bed2629ab1324ae46bd92f7b8e4630dec14ea3a"},
+    {file = "spacy_alignments-0.9.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dd0279610d5047205c8d10368a600fa6b9c6d995efdfb093708d54c9ad7efc1f"},
+    {file = "spacy_alignments-0.9.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9c152d78b25a88487145a6bb82aefc938e503c28c4249fd723390409deeb3f04"},
+    {file = "spacy_alignments-0.9.1-cp310-cp310-win_amd64.whl", hash = "sha256:61b42ba12222c1ea0e659ae5834e494f25492e7649425d0cef65aa8948818dd1"},
+    {file = "spacy_alignments-0.9.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:285babdffd85840164446fbc40435c57510d4b90f12e893bbecb55c690b23c51"},
+    {file = "spacy_alignments-0.9.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:3eb9cc7efe494468e61038f91269d66ca9a4aa3395250f60eb942368c19a6e11"},
+    {file = "spacy_alignments-0.9.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0dccd315b0d083dfae0c82f845e647ead16f04d2ec1c15c9fc05281d6ae00cf7"},
+    {file = "spacy_alignments-0.9.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c1fe1ad0bcc9f365746c4031d0523b52da79dd87f9c0e6e977c6c8fd4032a82b"},
+    {file = "spacy_alignments-0.9.1-cp311-cp311-win_amd64.whl", hash = "sha256:a58ce17fd919c3719529df17c34f82bbaec600130655294aa05effd2308baaeb"},
+    {file = "spacy_alignments-0.9.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:bf5a5d7b65f9c7dfbf9c9ac1d1a2ab3e1cdcfc93a1f52cef0d666c29b416fe7d"},
+    {file = "spacy_alignments-0.9.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:20644e71b2d685fc31013ac8a806224a9de4a4dd2c03ded621a95a95efc6000d"},
+    {file = "spacy_alignments-0.9.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:36825157fbd7b96e6bfeb3a0076dd36d8d1f560624b824c2873d10a1a0d70fd2"},
+    {file = "spacy_alignments-0.9.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:35fa7444dd7117e45cfca51335a4eb737627c9a9dfd191c8291cf9f5fb0557ae"},
+    {file = "spacy_alignments-0.9.1-cp312-cp312-win_amd64.whl", hash = "sha256:adb04d06cf417f5df56a80f1a54f9eedaab3e4165b4fcb50bf7c3680eb549fc6"},
+    {file = "spacy_alignments-0.9.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:1264e21f7fbba166ed02c8b495e99f2d92e43335a476f4afa498c02e32566b4e"},
+    {file = "spacy_alignments-0.9.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7fd8a59fe7d75a61d303e8a290cba53b82d85f3bfecaf267343ef47df5555e9d"},
+    {file = "spacy_alignments-0.9.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b4b97b879d614f1c37f330c0c0c2fcffacd6bf5322473169748aa76e4acbe484"},
+    {file = "spacy_alignments-0.9.1-cp37-cp37m-win_amd64.whl", hash = "sha256:c70df885671f75ed33371984ac156e5002c1245f0c64eb5a0b2aef20805b835b"},
+    {file = "spacy_alignments-0.9.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:c4e68df531d177d5b07ee9396f22c085e54685a6c4ab349f0ce5c8f55b54dde0"},
+    {file = "spacy_alignments-0.9.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:365c44a5f76d789af82d174235333f31cf0e151c28d56b886a1223a961b47ba4"},
+    {file = "spacy_alignments-0.9.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9c913af4e0e3da4acbd9265697fb86a2c8370b2e70d984ef8f7238efa2922ec9"},
+    {file = "spacy_alignments-0.9.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4582d242808c4c5c44380e3543e6a53225bf6db2ae9b4d9d58e2a671442e1b60"},
+    {file = "spacy_alignments-0.9.1-cp38-cp38-win_amd64.whl", hash = "sha256:69d8081654b310390aa037c6caee70fdf6825c4474f84dbe42d58cc44874c9f5"},
+    {file = "spacy_alignments-0.9.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:992e2768b6f2432922b616ca893fe7a66d3e865cf457352dc250bc16ab016633"},
+    {file = "spacy_alignments-0.9.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:10ecfb8e42adf0d39fec87bed9f344e0f85be893d2258d0b7d81134d5b110525"},
+    {file = "spacy_alignments-0.9.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:80f36d49431d6d6067c57caaabe1aca501bbe8df39c9ffa92daf386bdc239074"},
+    {file = "spacy_alignments-0.9.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b62c1d70bfb6fc12ce2a7a92f1c1725abaa87a0e06bc2c4bf2b3b5b43f5a3f59"},
+    {file = "spacy_alignments-0.9.1-cp39-cp39-win_amd64.whl", hash = "sha256:0b3cd95356f27fa4dc41448e131b6b44eb065d11e4c4c4fbcbfc0ef20ad4e513"},
+]
+
 [[package]]
 name = "spacy-legacy"
 version = "3.0.12"
@@ -2379,6 +2831,68 @@ files = [
     {file = "spacy_loggers-1.0.5-py3-none-any.whl", hash = "sha256:196284c9c446cc0cdb944005384270d775fdeaf4f494d8e269466cfa497ef645"},
 ]
 
+[[package]]
+name = "spacy-transformers"
+version = "1.3.5"
+description = "spaCy pipelines for pre-trained BERT and other transformers"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "spacy_transformers-1.3.5-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:7f74f47a1d8b86d50c8ad6bba8334852cf19001e776b0c4a1f580bc0387d2f43"},
+    {file = "spacy_transformers-1.3.5-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:75de3cb416e8fae2195b7d88178133fd9a350aa266a24995e826b4304fb2d105"},
+    {file = "spacy_transformers-1.3.5-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1e1a5fcf3d486111c46ee4c6e767e32e1ddda4f3f0c06feac0a987687bf6594f"},
+    {file = "spacy_transformers-1.3.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6db43ea2a79b8dfcb7742d935af125d8f8daea2c4b5d33e933f246e348688cf0"},
+    {file = "spacy_transformers-1.3.5-cp310-cp310-win_amd64.whl", hash = "sha256:961a631cbf724847db280822df972dd5d05d39a70c21310da3e431fea4164dff"},
+    {file = "spacy_transformers-1.3.5-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6a0de2c301864ece1eb84b5249ff1b0a7a01900cc26bb67f72eea00146d06b9f"},
+    {file = "spacy_transformers-1.3.5-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:c0aa0a2cc401414d48a5cfc6c13bbedabb07dc672c384f5594ec5d578ff9e6a5"},
+    {file = "spacy_transformers-1.3.5-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c39e546f5f44a6838a290b986e7f6f8aa7d2613962cf753dc16e18da932be0ae"},
+    {file = "spacy_transformers-1.3.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47f72d35f5aa4f88e0f3b9ff62a29985bff6ba940d13ba20ca165d61241b8410"},
+    {file = "spacy_transformers-1.3.5-cp311-cp311-win_amd64.whl", hash = "sha256:2b6c1152e19d0f8dfb79febcf6792f43e31acb76b836b3b57fa2cc7dd9c11c28"},
+    {file = "spacy_transformers-1.3.5-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:0aa12d703c58a3423ad913c99f5056b71963d000126336406262ba4d6474f22f"},
+    {file = "spacy_transformers-1.3.5-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:8e7fdb8b1b12d4a07a4bf5af98ab7035830030594c8900b681644b4cfdffddf2"},
+    {file = "spacy_transformers-1.3.5-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:29dbde65d88cd9f14f05c3428558f5cb981e7b5c9374aac9f83fb786d5c6bf2c"},
+    {file = "spacy_transformers-1.3.5-cp312-cp312-win_amd64.whl", hash = "sha256:ab5b79775f1a9b12370f86a4b282a5d9889fdb067305203e81fc4ec990cbc737"},
+    {file = "spacy_transformers-1.3.5-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:474db46a6a12f5fba37f52adafed6b8a83b488d4bc4b532fd5f70489c5d7d232"},
+    {file = "spacy_transformers-1.3.5-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b69f60113ecf7465aeb008ec8aad93ad9ef0c4472709c339cd80f9973f878af9"},
+    {file = "spacy_transformers-1.3.5-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9668bdc13dbd9f586d13f4e1e58ec6dba6108d08150ca2387c92a08caeedd184"},
+    {file = "spacy_transformers-1.3.5-cp37-cp37m-win_amd64.whl", hash = "sha256:e81aaab478f9bffe4c3aba22ab5afb2809c737ac23bbea553ceb0802538cf918"},
+    {file = "spacy_transformers-1.3.5-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:43a4f1da7dc05236cd9dbe9260dddfca7a4307805aecde0346cbc809ecf45892"},
+    {file = "spacy_transformers-1.3.5-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:6ee966fdc83d1b5b3258cc19e40719a18380e99f286207216588fb0e7247745f"},
+    {file = "spacy_transformers-1.3.5-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ef54d2e00e5f1934ae7d2a09bc0fece79d628ebaf0ce733dd852fbce49e25773"},
+    {file = "spacy_transformers-1.3.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b610d757e0617088e400e38d8118f0f911324b62eb63d2ff813caf6477181b8"},
+    {file = "spacy_transformers-1.3.5-cp38-cp38-win_amd64.whl", hash = "sha256:e02ee6e029fc6c9250ef6083743446c64007b4baee1de7d29c994c0103756aa9"},
+    {file = "spacy_transformers-1.3.5-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:75fa1ff1b511ddb81c7a3b69a731635abb9a0b360413db77f788e81b4b06719f"},
+    {file = "spacy_transformers-1.3.5-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:5f184c117d427227266d623ffc456b2221a487616b3dd7e6262ba60bd34e604f"},
+    {file = "spacy_transformers-1.3.5-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9ae85cf563a771f060520de6b360ebec87a7344ae44b36429b75db0038ba55c6"},
+    {file = "spacy_transformers-1.3.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0284256371ec1e15f1e1a6b541efd9d5462c6484e9d447f2da1bc76aee5ffa1e"},
+    {file = "spacy_transformers-1.3.5-cp39-cp39-win_amd64.whl", hash = "sha256:44392a83189e52faf5adc3ae8daff17e9eae543c81ab7f3cb8265670acc8c82a"},
+    {file = "spacy_transformers-1.3.5.tar.gz", hash = "sha256:accdfe44a26517714c6990ec6bae88796eb348286fea7ba20ba2736f70c83fa1"},
+]
+
+[package.dependencies]
+numpy = [
+    {version = ">=1.15.0", markers = "python_version < \"3.9\""},
+    {version = ">=1.19.0", markers = "python_version >= \"3.9\""},
+]
+spacy = ">=3.5.0,<4.1.0"
+spacy-alignments = ">=0.7.2,<1.0.0"
+srsly = ">=2.4.0,<3.0.0"
+torch = ">=1.8.0"
+transformers = ">=3.4.0,<4.37.0"
+
+[package.extras]
+cuda = ["cupy (>=5.0.0b4)"]
+cuda100 = ["cupy-cuda100 (>=5.0.0b4)"]
+cuda101 = ["cupy-cuda101 (>=5.0.0b4)"]
+cuda102 = ["cupy-cuda102 (>=5.0.0b4)"]
+cuda110 = ["cupy-cuda110 (>=5.0.0b4)"]
+cuda111 = ["cupy-cuda111 (>=5.0.0b4)"]
+cuda112 = ["cupy-cuda112 (>=5.0.0b4)"]
+cuda80 = ["cupy-cuda80 (>=5.0.0b4)"]
+cuda90 = ["cupy-cuda90 (>=5.0.0b4)"]
+cuda91 = ["cupy-cuda91 (>=5.0.0b4)"]
+cuda92 = ["cupy-cuda92 (>=5.0.0b4)"]
+
 [[package]]
 name = "srsly"
 version = "2.4.8"
@@ -2444,6 +2958,36 @@ pure-eval = "*"
 [package.extras]
 tests = ["cython", "littleutils", "pygments", "pytest", "typeguard"]
 
+[[package]]
+name = "sympy"
+version = "1.13.0"
+description = "Computer algebra system (CAS) in Python"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "sympy-1.13.0-py3-none-any.whl", hash = "sha256:6b0b32a4673fb91bd3cac3b55406c8e01d53ae22780be467301cc452f6680c92"},
+    {file = "sympy-1.13.0.tar.gz", hash = "sha256:3b6af8f4d008b9a1a6a4268b335b984b23835f26d1d60b0526ebc71d48a25f57"},
+]
+
+[package.dependencies]
+mpmath = ">=1.1.0,<1.4"
+
+[package.extras]
+dev = ["hypothesis (>=6.70.0)", "pytest (>=7.1.0)"]
+
+[[package]]
+name = "tbb"
+version = "2021.13.0"
+description = "Intel® oneAPI Threading Building Blocks (oneTBB)"
+optional = false
+python-versions = "*"
+files = [
+    {file = "tbb-2021.13.0-py2.py3-none-manylinux1_i686.whl", hash = "sha256:a2567725329639519d46d92a2634cf61e76601dac2f777a05686fea546c4fe4f"},
+    {file = "tbb-2021.13.0-py2.py3-none-manylinux1_x86_64.whl", hash = "sha256:aaf667e92849adb012b8874d6393282afc318aca4407fc62f912ee30a22da46a"},
+    {file = "tbb-2021.13.0-py3-none-win32.whl", hash = "sha256:6669d26703e9943f6164c6407bd4a237a45007e79b8d3832fe6999576eaaa9ef"},
+    {file = "tbb-2021.13.0-py3-none-win_amd64.whl", hash = "sha256:3528a53e4bbe64b07a6112b4c5a00ff3c61924ee46c9c68e004a1ac7ad1f09c3"},
+]
+
 [[package]]
 name = "text2num"
 version = "2.5.1"
@@ -2540,6 +3084,198 @@ mxnet = ["mxnet (>=1.5.1,<1.6.0)"]
 tensorflow = ["tensorflow (>=2.0.0,<2.6.0)"]
 torch = ["torch (>=1.6.0)"]
 
+[[package]]
+name = "tokenizers"
+version = "0.15.2"
+description = ""
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "tokenizers-0.15.2-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:52f6130c9cbf70544287575a985bf44ae1bda2da7e8c24e97716080593638012"},
+    {file = "tokenizers-0.15.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:054c1cc9c6d68f7ffa4e810b3d5131e0ba511b6e4be34157aa08ee54c2f8d9ee"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:a9b9b070fdad06e347563b88c278995735292ded1132f8657084989a4c84a6d5"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ea621a7eef4b70e1f7a4e84dd989ae3f0eeb50fc8690254eacc08acb623e82f1"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:cf7fd9a5141634fa3aa8d6b7be362e6ae1b4cda60da81388fa533e0b552c98fd"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:44f2a832cd0825295f7179eaf173381dc45230f9227ec4b44378322d900447c9"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8b9ec69247a23747669ec4b0ca10f8e3dfb3545d550258129bd62291aabe8605"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:40b6a4c78da863ff26dbd5ad9a8ecc33d8a8d97b535172601cf00aee9d7ce9ce"},
+    {file = "tokenizers-0.15.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:5ab2a4d21dcf76af60e05af8063138849eb1d6553a0d059f6534357bce8ba364"},
+    {file = "tokenizers-0.15.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a47acfac7e511f6bbfcf2d3fb8c26979c780a91e06fb5b9a43831b2c0153d024"},
+    {file = "tokenizers-0.15.2-cp310-none-win32.whl", hash = "sha256:064ff87bb6acdbd693666de9a4b692add41308a2c0ec0770d6385737117215f2"},
+    {file = "tokenizers-0.15.2-cp310-none-win_amd64.whl", hash = "sha256:3b919afe4df7eb6ac7cafd2bd14fb507d3f408db7a68c43117f579c984a73843"},
+    {file = "tokenizers-0.15.2-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:89cd1cb93e4b12ff39bb2d626ad77e35209de9309a71e4d3d4672667b4b256e7"},
+    {file = "tokenizers-0.15.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:cfed5c64e5be23d7ee0f0e98081a25c2a46b0b77ce99a4f0605b1ec43dd481fa"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:a907d76dcfda37023ba203ab4ceeb21bc5683436ebefbd895a0841fd52f6f6f2"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:20ea60479de6fc7b8ae756b4b097572372d7e4032e2521c1bbf3d90c90a99ff0"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:48e2b9335be2bc0171df9281385c2ed06a15f5cf121c44094338306ab7b33f2c"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:112a1dd436d2cc06e6ffdc0b06d55ac019a35a63afd26475205cb4b1bf0bfbff"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4620cca5c2817177ee8706f860364cc3a8845bc1e291aaf661fb899e5d1c45b0"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ccd73a82751c523b3fc31ff8194702e4af4db21dc20e55b30ecc2079c5d43cb7"},
+    {file = "tokenizers-0.15.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:107089f135b4ae7817affe6264f8c7a5c5b4fd9a90f9439ed495f54fcea56fb4"},
+    {file = "tokenizers-0.15.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:0ff110ecc57b7aa4a594396525a3451ad70988e517237fe91c540997c4e50e29"},
+    {file = "tokenizers-0.15.2-cp311-none-win32.whl", hash = "sha256:6d76f00f5c32da36c61f41c58346a4fa7f0a61be02f4301fd30ad59834977cc3"},
+    {file = "tokenizers-0.15.2-cp311-none-win_amd64.whl", hash = "sha256:cc90102ed17271cf0a1262babe5939e0134b3890345d11a19c3145184b706055"},
+    {file = "tokenizers-0.15.2-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:f86593c18d2e6248e72fb91c77d413a815153b8ea4e31f7cd443bdf28e467670"},
+    {file = "tokenizers-0.15.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:0774bccc6608eca23eb9d620196687c8b2360624619623cf4ba9dc9bd53e8b51"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:d0222c5b7c9b26c0b4822a82f6a7011de0a9d3060e1da176f66274b70f846b98"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3835738be1de66624fff2f4f6f6684775da4e9c00bde053be7564cbf3545cc66"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:0143e7d9dcd811855c1ce1ab9bf5d96d29bf5e528fd6c7824d0465741e8c10fd"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:db35825f6d54215f6b6009a7ff3eedee0848c99a6271c870d2826fbbedf31a38"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3f5e64b0389a2be47091d8cc53c87859783b837ea1a06edd9d8e04004df55a5c"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9e0480c452217edd35eca56fafe2029fb4d368b7c0475f8dfa3c5c9c400a7456"},
+    {file = "tokenizers-0.15.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:a33ab881c8fe70474980577e033d0bc9a27b7ab8272896e500708b212995d834"},
+    {file = "tokenizers-0.15.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:a308a607ca9de2c64c1b9ba79ec9a403969715a1b8ba5f998a676826f1a7039d"},
+    {file = "tokenizers-0.15.2-cp312-none-win32.whl", hash = "sha256:b8fcfa81bcb9447df582c5bc96a031e6df4da2a774b8080d4f02c0c16b42be0b"},
+    {file = "tokenizers-0.15.2-cp312-none-win_amd64.whl", hash = "sha256:38d7ab43c6825abfc0b661d95f39c7f8af2449364f01d331f3b51c94dcff7221"},
+    {file = "tokenizers-0.15.2-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:38bfb0204ff3246ca4d5e726e8cc8403bfc931090151e6eede54d0e0cf162ef0"},
+    {file = "tokenizers-0.15.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:9c861d35e8286a53e06e9e28d030b5a05bcbf5ac9d7229e561e53c352a85b1fc"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:936bf3842db5b2048eaa53dade907b1160f318e7c90c74bfab86f1e47720bdd6"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:620beacc3373277700d0e27718aa8b25f7b383eb8001fba94ee00aeea1459d89"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:2735ecbbf37e52db4ea970e539fd2d450d213517b77745114f92867f3fc246eb"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:473c83c5e2359bb81b0b6fde870b41b2764fcdd36d997485e07e72cc3a62264a"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:968fa1fb3c27398b28a4eca1cbd1e19355c4d3a6007f7398d48826bbe3a0f728"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:865c60ae6eaebdde7da66191ee9b7db52e542ed8ee9d2c653b6d190a9351b980"},
+    {file = "tokenizers-0.15.2-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:7c0d8b52664ab2d4a8d6686eb5effc68b78608a9008f086a122a7b2996befbab"},
+    {file = "tokenizers-0.15.2-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:f33dfbdec3784093a9aebb3680d1f91336c56d86cc70ddf88708251da1fe9064"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-macosx_10_12_x86_64.whl", hash = "sha256:d44ba80988ff9424e33e0a49445072ac7029d8c0e1601ad25a0ca5f41ed0c1d6"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-macosx_11_0_arm64.whl", hash = "sha256:dce74266919b892f82b1b86025a613956ea0ea62a4843d4c4237be2c5498ed3a"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:0ef06b9707baeb98b316577acb04f4852239d856b93e9ec3a299622f6084e4be"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c73e2e74bbb07910da0d37c326869f34113137b23eadad3fc00856e6b3d9930c"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:4eeb12daf02a59e29f578a865f55d87cd103ce62bd8a3a5874f8fdeaa82e336b"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9ba9f6895af58487ca4f54e8a664a322f16c26bbb442effd01087eba391a719e"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ccec77aa7150e38eec6878a493bf8c263ff1fa8a62404e16c6203c64c1f16a26"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f3f40604f5042ff210ba82743dda2b6aa3e55aa12df4e9f2378ee01a17e2855e"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:5645938a42d78c4885086767c70923abad047163d809c16da75d6b290cb30bbe"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:05a77cbfebe28a61ab5c3891f9939cc24798b63fa236d84e5f29f3a85a200c00"},
+    {file = "tokenizers-0.15.2-cp37-none-win32.whl", hash = "sha256:361abdc068e8afe9c5b818769a48624687fb6aaed49636ee39bec4e95e1a215b"},
+    {file = "tokenizers-0.15.2-cp37-none-win_amd64.whl", hash = "sha256:7ef789f83eb0f9baeb4d09a86cd639c0a5518528f9992f38b28e819df397eb06"},
+    {file = "tokenizers-0.15.2-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:4fe1f74a902bee74a3b25aff180fbfbf4f8b444ab37c4d496af7afd13a784ed2"},
+    {file = "tokenizers-0.15.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:4c4b89038a684f40a6b15d6b09f49650ac64d951ad0f2a3ea9169687bbf2a8ba"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:d05a1b06f986d41aed5f2de464c003004b2df8aaf66f2b7628254bcbfb72a438"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:508711a108684111ec8af89d3a9e9e08755247eda27d0ba5e3c50e9da1600f6d"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:daa348f02d15160cb35439098ac96e3a53bacf35885072611cd9e5be7d333daa"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:494fdbe5932d3416de2a85fc2470b797e6f3226c12845cadf054dd906afd0442"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c2d60f5246f4da9373f75ff18d64c69cbf60c3bca597290cea01059c336d2470"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:93268e788825f52de4c7bdcb6ebc1fcd4a5442c02e730faa9b6b08f23ead0e24"},
+    {file = "tokenizers-0.15.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:6fc7083ab404019fc9acafe78662c192673c1e696bd598d16dc005bd663a5cf9"},
+    {file = "tokenizers-0.15.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:41e39b41e5531d6b2122a77532dbea60e171ef87a3820b5a3888daa847df4153"},
+    {file = "tokenizers-0.15.2-cp38-none-win32.whl", hash = "sha256:06cd0487b1cbfabefb2cc52fbd6b1f8d4c37799bd6c6e1641281adaa6b2504a7"},
+    {file = "tokenizers-0.15.2-cp38-none-win_amd64.whl", hash = "sha256:5179c271aa5de9c71712e31cb5a79e436ecd0d7532a408fa42a8dbfa4bc23fd9"},
+    {file = "tokenizers-0.15.2-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:82f8652a74cc107052328b87ea8b34291c0f55b96d8fb261b3880216a9f9e48e"},
+    {file = "tokenizers-0.15.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:02458bee6f5f3139f1ebbb6d042b283af712c0981f5bc50edf771d6b762d5e4f"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:c9a09cd26cca2e1c349f91aa665309ddb48d71636370749414fbf67bc83c5343"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:158be8ea8554e5ed69acc1ce3fbb23a06060bd4bbb09029431ad6b9a466a7121"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:1ddba9a2b0c8c81633eca0bb2e1aa5b3a15362b1277f1ae64176d0f6eba78ab1"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3ef5dd1d39797044642dbe53eb2bc56435308432e9c7907728da74c69ee2adca"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:454c203164e07a860dbeb3b1f4a733be52b0edbb4dd2e5bd75023ffa8b49403a"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0cf6b7f1d4dc59af960e6ffdc4faffe6460bbfa8dce27a58bf75755ffdb2526d"},
+    {file = "tokenizers-0.15.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:2ef09bbc16519f6c25d0c7fc0c6a33a6f62923e263c9d7cca4e58b8c61572afb"},
+    {file = "tokenizers-0.15.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:c9a2ebdd2ad4ec7a68e7615086e633857c85e2f18025bd05d2a4399e6c5f7169"},
+    {file = "tokenizers-0.15.2-cp39-none-win32.whl", hash = "sha256:918fbb0eab96fe08e72a8c2b5461e9cce95585d82a58688e7f01c2bd546c79d0"},
+    {file = "tokenizers-0.15.2-cp39-none-win_amd64.whl", hash = "sha256:524e60da0135e106b254bd71f0659be9f89d83f006ea9093ce4d1fab498c6d0d"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:6a9b648a58281c4672212fab04e60648fde574877d0139cd4b4f93fe28ca8944"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:7c7d18b733be6bbca8a55084027f7be428c947ddf871c500ee603e375013ffba"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:13ca3611de8d9ddfbc4dc39ef54ab1d2d4aaa114ac8727dfdc6a6ec4be017378"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:237d1bf3361cf2e6463e6c140628e6406766e8b27274f5fcc62c747ae3c6f094"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:67a0fe1e49e60c664915e9fb6b0cb19bac082ab1f309188230e4b2920230edb3"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:4e022fe65e99230b8fd89ebdfea138c24421f91c1a4f4781a8f5016fd5cdfb4d"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:d857be2df69763362ac699f8b251a8cd3fac9d21893de129bc788f8baaef2693"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-macosx_10_12_x86_64.whl", hash = "sha256:708bb3e4283177236309e698da5fcd0879ce8fd37457d7c266d16b550bcbbd18"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:64c35e09e9899b72a76e762f9854e8750213f67567787d45f37ce06daf57ca78"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c1257f4394be0d3b00de8c9e840ca5601d0a4a8438361ce9c2b05c7d25f6057b"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:02272fe48280e0293a04245ca5d919b2c94a48b408b55e858feae9618138aeda"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:dc3ad9ebc76eabe8b1d7c04d38be884b8f9d60c0cdc09b0aa4e3bcf746de0388"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:32e16bdeffa7c4f46bf2152172ca511808b952701d13e7c18833c0b73cb5c23f"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:fb16ba563d59003028b678d2361a27f7e4ae0ab29c7a80690efa20d829c81fdb"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:2277c36d2d6cdb7876c274547921a42425b6810d38354327dd65a8009acf870c"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:1cf75d32e8d250781940d07f7eece253f2fe9ecdb1dc7ba6e3833fa17b82fcbc"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f1b3b31884dc8e9b21508bb76da80ebf7308fdb947a17affce815665d5c4d028"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b10122d8d8e30afb43bb1fe21a3619f62c3e2574bff2699cf8af8b0b6c5dc4a3"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:d88b96ff0fe8e91f6ef01ba50b0d71db5017fa4e3b1d99681cec89a85faf7bf7"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:37aaec5a52e959892870a7c47cef80c53797c0db9149d458460f4f31e2fb250e"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:e2ea752f2b0fe96eb6e2f3adbbf4d72aaa1272079b0dfa1145507bd6a5d537e6"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:4b19a808d8799fda23504a5cd31d2f58e6f52f140380082b352f877017d6342b"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:64c86e5e068ac8b19204419ed8ca90f9d25db20578f5881e337d203b314f4104"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:de19c4dc503c612847edf833c82e9f73cd79926a384af9d801dcf93f110cea4e"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ea09acd2fe3324174063d61ad620dec3bcf042b495515f27f638270a7d466e8b"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:cf27fd43472e07b57cf420eee1e814549203d56de00b5af8659cb99885472f1f"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:7ca22bd897537a0080521445d91a58886c8c04084a6a19e6c78c586e0cfa92a5"},
+    {file = "tokenizers-0.15.2.tar.gz", hash = "sha256:e6e9c6e019dd5484be5beafc775ae6c925f4c69a3487040ed09b45e13df2cb91"},
+]
+
+[package.dependencies]
+huggingface_hub = ">=0.16.4,<1.0"
+
+[package.extras]
+dev = ["tokenizers[testing]"]
+docs = ["setuptools_rust", "sphinx", "sphinx_rtd_theme"]
+testing = ["black (==22.3)", "datasets", "numpy", "pytest", "requests"]
+
+[[package]]
+name = "tomli"
+version = "2.0.1"
+description = "A lil' TOML parser"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"},
+    {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
+]
+
+[[package]]
+name = "torch"
+version = "2.3.1"
+description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration"
+optional = false
+python-versions = ">=3.8.0"
+files = [
+    {file = "torch-2.3.1-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:605a25b23944be5ab7c3467e843580e1d888b8066e5aaf17ff7bf9cc30001cc3"},
+    {file = "torch-2.3.1-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:f2357eb0965583a0954d6f9ad005bba0091f956aef879822274b1bcdb11bd308"},
+    {file = "torch-2.3.1-cp310-cp310-win_amd64.whl", hash = "sha256:32b05fe0d1ada7f69c9f86c14ff69b0ef1957a5a54199bacba63d22d8fab720b"},
+    {file = "torch-2.3.1-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:7c09a94362778428484bcf995f6004b04952106aee0ef45ff0b4bab484f5498d"},
+    {file = "torch-2.3.1-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:b2ec81b61bb094ea4a9dee1cd3f7b76a44555375719ad29f05c0ca8ef596ad39"},
+    {file = "torch-2.3.1-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:490cc3d917d1fe0bd027057dfe9941dc1d6d8e3cae76140f5dd9a7e5bc7130ab"},
+    {file = "torch-2.3.1-cp311-cp311-win_amd64.whl", hash = "sha256:5802530783bd465fe66c2df99123c9a54be06da118fbd785a25ab0a88123758a"},
+    {file = "torch-2.3.1-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:a7dd4ed388ad1f3d502bf09453d5fe596c7b121de7e0cfaca1e2017782e9bbac"},
+    {file = "torch-2.3.1-cp312-cp312-manylinux1_x86_64.whl", hash = "sha256:a486c0b1976a118805fc7c9641d02df7afbb0c21e6b555d3bb985c9f9601b61a"},
+    {file = "torch-2.3.1-cp312-cp312-manylinux2014_aarch64.whl", hash = "sha256:224259821fe3e4c6f7edf1528e4fe4ac779c77addaa74215eb0b63a5c474d66c"},
+    {file = "torch-2.3.1-cp312-cp312-win_amd64.whl", hash = "sha256:e5fdccbf6f1334b2203a61a0e03821d5845f1421defe311dabeae2fc8fbeac2d"},
+    {file = "torch-2.3.1-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:3c333dc2ebc189561514eda06e81df22bf8fb64e2384746b2cb9f04f96d1d4c8"},
+    {file = "torch-2.3.1-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:07e9ba746832b8d069cacb45f312cadd8ad02b81ea527ec9766c0e7404bb3feb"},
+    {file = "torch-2.3.1-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:462d1c07dbf6bb5d9d2f3316fee73a24f3d12cd8dacf681ad46ef6418f7f6626"},
+    {file = "torch-2.3.1-cp38-cp38-win_amd64.whl", hash = "sha256:ff60bf7ce3de1d43ad3f6969983f321a31f0a45df3690921720bcad6a8596cc4"},
+    {file = "torch-2.3.1-cp38-none-macosx_11_0_arm64.whl", hash = "sha256:bee0bd33dc58aa8fc8a7527876e9b9a0e812ad08122054a5bff2ce5abf005b10"},
+    {file = "torch-2.3.1-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:aaa872abde9a3d4f91580f6396d54888620f4a0b92e3976a6034759df4b961ad"},
+    {file = "torch-2.3.1-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:3d7a7f7ef21a7520510553dc3938b0c57c116a7daee20736a9e25cbc0e832bdc"},
+    {file = "torch-2.3.1-cp39-cp39-win_amd64.whl", hash = "sha256:4777f6cefa0c2b5fa87223c213e7b6f417cf254a45e5829be4ccd1b2a4ee1011"},
+    {file = "torch-2.3.1-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:2bb5af780c55be68fe100feb0528d2edebace1d55cb2e351de735809ba7391eb"},
+]
+
+[package.dependencies]
+filelock = "*"
+fsspec = "*"
+jinja2 = "*"
+mkl = {version = ">=2021.1.1,<=2021.4.0", markers = "platform_system == \"Windows\""}
+networkx = "*"
+nvidia-cublas-cu12 = {version = "12.1.3.1", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-cupti-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-nvrtc-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-runtime-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cudnn-cu12 = {version = "8.9.2.26", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cufft-cu12 = {version = "11.0.2.54", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-curand-cu12 = {version = "10.3.2.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cusolver-cu12 = {version = "11.4.5.107", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cusparse-cu12 = {version = "12.1.0.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-nccl-cu12 = {version = "2.20.5", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-nvtx-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+sympy = "*"
+triton = {version = "2.3.1", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version < \"3.12\""}
+typing-extensions = ">=4.8.0"
+
+[package.extras]
+opt-einsum = ["opt-einsum (>=3.3)"]
+optree = ["optree (>=0.9.1)"]
+
 [[package]]
 name = "tornado"
 version = "6.4"
@@ -2595,6 +3331,97 @@ files = [
 docs = ["myst-parser", "pydata-sphinx-theme", "sphinx"]
 test = ["argcomplete (>=3.0.3)", "mypy (>=1.7.0)", "pre-commit", "pytest (>=7.0,<8.2)", "pytest-mock", "pytest-mypy-testing"]
 
+[[package]]
+name = "transformers"
+version = "4.36.2"
+description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
+optional = false
+python-versions = ">=3.8.0"
+files = [
+    {file = "transformers-4.36.2-py3-none-any.whl", hash = "sha256:462066c4f74ee52516f12890dcc9ec71d1a5e97998db621668455117a54330f6"},
+    {file = "transformers-4.36.2.tar.gz", hash = "sha256:d8068e897e47793281501e547d2bbdfc5b8556409c2cb6c3d9e2ca77d4c0b4ec"},
+]
+
+[package.dependencies]
+filelock = "*"
+huggingface-hub = ">=0.19.3,<1.0"
+numpy = ">=1.17"
+packaging = ">=20.0"
+pyyaml = ">=5.1"
+regex = "!=2019.12.17"
+requests = "*"
+safetensors = ">=0.3.1"
+tokenizers = ">=0.14,<0.19"
+tqdm = ">=4.27"
+
+[package.extras]
+accelerate = ["accelerate (>=0.21.0)"]
+agents = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "datasets (!=2.5.0)", "diffusers", "opencv-python", "sentencepiece (>=0.1.91,!=0.1.92)", "torch (>=1.10,!=1.12.0)"]
+all = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune] (>=2.7.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timm", "tokenizers (>=0.14,<0.19)", "torch (>=1.10,!=1.12.0)", "torchaudio", "torchvision"]
+audio = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
+codecarbon = ["codecarbon (==1.2.0)"]
+deepspeed = ["accelerate (>=0.21.0)", "deepspeed (>=0.9.3)"]
+deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.21.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.9.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "optuna", "parameterized", "protobuf", "psutil", "pydantic (<2)", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"]
+dev = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "decord (==0.6.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "flax (>=0.4.1,<=0.7.0)", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic (<2)", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "timm", "tokenizers (>=0.14,<0.19)", "torch (>=1.10,!=1.12.0)", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
+dev-tensorflow = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "isort (>=5.5.4)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic (<2)", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "tokenizers (>=0.14,<0.19)", "urllib3 (<2.0.0)"]
+dev-torch = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "kenlm", "librosa", "nltk", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic (<2)", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "timeout-decorator", "timm", "tokenizers (>=0.14,<0.19)", "torch (>=1.10,!=1.12.0)", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
+docs = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "hf-doc-builder", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune] (>=2.7.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timm", "tokenizers (>=0.14,<0.19)", "torch (>=1.10,!=1.12.0)", "torchaudio", "torchvision"]
+docs-specific = ["hf-doc-builder"]
+flax = ["flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "optax (>=0.0.8,<=0.1.4)"]
+flax-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
+ftfy = ["ftfy"]
+integrations = ["optuna", "ray[tune] (>=2.7.0)", "sigopt"]
+ja = ["fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "rhoknp (>=1.1.0,<1.3.1)", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)"]
+modelcreation = ["cookiecutter (==1.7.3)"]
+natten = ["natten (>=0.14.6)"]
+onnx = ["onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "tf2onnx"]
+onnxruntime = ["onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"]
+optuna = ["optuna"]
+quality = ["GitPython (<3.1.19)", "datasets (!=2.5.0)", "hf-doc-builder (>=0.3.0)", "isort (>=5.5.4)", "ruff (==0.1.5)", "urllib3 (<2.0.0)"]
+ray = ["ray[tune] (>=2.7.0)"]
+retrieval = ["datasets (!=2.5.0)", "faiss-cpu"]
+sagemaker = ["sagemaker (>=2.31.0)"]
+sentencepiece = ["protobuf", "sentencepiece (>=0.1.91,!=0.1.92)"]
+serving = ["fastapi", "pydantic (<2)", "starlette", "uvicorn"]
+sigopt = ["sigopt"]
+sklearn = ["scikit-learn"]
+speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
+testing = ["GitPython (<3.1.19)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "parameterized", "protobuf", "psutil", "pydantic (<2)", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "tensorboard", "timeout-decorator"]
+tf = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"]
+tf-cpu = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow-cpu (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"]
+tf-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
+timm = ["timm"]
+tokenizers = ["tokenizers (>=0.14,<0.19)"]
+torch = ["accelerate (>=0.21.0)", "torch (>=1.10,!=1.12.0)"]
+torch-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
+torch-vision = ["Pillow (>=10.0.1,<=15.0)", "torchvision"]
+torchhub = ["filelock", "huggingface-hub (>=0.19.3,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.14,<0.19)", "torch (>=1.10,!=1.12.0)", "tqdm (>=4.27)"]
+video = ["av (==9.2.0)", "decord (==0.6.0)"]
+vision = ["Pillow (>=10.0.1,<=15.0)"]
+
+[[package]]
+name = "triton"
+version = "2.3.1"
+description = "A language and compiler for custom Deep Learning operations"
+optional = false
+python-versions = "*"
+files = [
+    {file = "triton-2.3.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3c84595cbe5e546b1b290d2a58b1494df5a2ef066dd890655e5b8a8a92205c33"},
+    {file = "triton-2.3.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c9d64ae33bcb3a7a18081e3a746e8cf87ca8623ca13d2c362413ce7a486f893e"},
+    {file = "triton-2.3.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:eaf80e8761a9e3498aa92e7bf83a085b31959c61f5e8ac14eedd018df6fccd10"},
+    {file = "triton-2.3.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b13bf35a2b659af7159bf78e92798dc62d877aa991de723937329e2d382f1991"},
+    {file = "triton-2.3.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:63381e35ded3304704ea867ffde3b7cfc42c16a55b3062d41e017ef510433d66"},
+    {file = "triton-2.3.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1d968264523c7a07911c8fb51b4e0d1b920204dae71491b1fe7b01b62a31e124"},
+]
+
+[package.dependencies]
+filelock = "*"
+
+[package.extras]
+build = ["cmake (>=3.20)", "lit"]
+tests = ["autopep8", "flake8", "isort", "numpy", "pytest", "scipy (>=1.7.1)", "torch"]
+tutorials = ["matplotlib", "pandas", "tabulate", "torch"]
+
 [[package]]
 name = "typer"
 version = "0.9.4"
@@ -2772,4 +3599,4 @@ testing = ["big-O", "jaraco.functools", "jaraco.itertools", "more-itertools", "p
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.8,<3.12"
-content-hash = "71381954b1201b8da9166741744c4d4102331cf54ae02a0e92b404f521cf4a2e"
+content-hash = "76ef03d6b54812192c469fd25e89482d075727dce07a1d01e2439db8babb928f"
diff --git a/pyproject.toml b/pyproject.toml
index 0106a9901..c7ddb7e04 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -14,13 +14,14 @@ text2num = "^2.5.0"
 pandas = "^2.0.0"
 shortuuid = "^1.0.13"
 pre-commit = "^3.2.0"
-spacy = "^3.7.4"
+spacy = {extras = ["transformers"], version = "^3.7.5"}
 regex = "^2023.12.25"
 num2words = "^0.5.13"
 geopy = "^2.4.1"
 requests-cache = "^1.2.0"
 pycountry = "22.3.5"
 fastparquet = "2023.10.1"
+pytest = "^8.2.2"
 
 [tool.poetry.group.dev.dependencies]
 ipykernel = "^6.29.3"
diff --git a/pytest.ini b/pytest.ini
new file mode 100644
index 000000000..768a60430
--- /dev/null
+++ b/pytest.ini
@@ -0,0 +1,12 @@
+
+[pytest]
+testpaths = tests
+python_files = test_*.py
+addopts = -rf --import-mode=importlib
+pythonpath = .
+
+[tool.pytest.ini_options]
+log_cli = true
+log_cli_level = "INFO"
+log_cli_format = "%(asctime)s [%(levelname)8s] %(message)s (%(filename)s:%(lineno)s)"
+log_cli_date_format = "%Y-%m-%d %H:%M:%S"
diff --git a/tests/specific_instance_eval/test_gold_list_death.parquet b/tests/specific_instance_eval/test_gold_list_death.parquet
new file mode 100644
index 000000000..626f7861d
--- /dev/null
+++ b/tests/specific_instance_eval/test_gold_list_death.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b6c58941d521870609b56226511726ae68596d49205a3b6b09ee793b372c071
+size 11610
diff --git a/tests/specific_instance_eval/test_sys_list_death.parquet b/tests/specific_instance_eval/test_sys_list_death.parquet
new file mode 100644
index 000000000..61950344d
--- /dev/null
+++ b/tests/specific_instance_eval/test_sys_list_death.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4def986f0d4de7c8bb5e8fc84c886dc4d9c5d01004d1d8466eb22d83ce6e283d
+size 9050
diff --git a/tests/test_specific_instance_matcher.py b/tests/test_specific_instance_matcher.py
new file mode 100644
index 000000000..cdcb32a56
--- /dev/null
+++ b/tests/test_specific_instance_matcher.py
@@ -0,0 +1,216 @@
+import pytest
+
+from Evaluation.matcher import SpecificInstanceMatcher
+
+
+class TestSpecificInstanceMatcher:
+    @pytest.mark.parametrize(
+        "gold_instance, sys_list, expected",
+        [
+            (
+                {"Num_Min": 0, "Num_Max": 10, "Start_Date_Year": 2030},
+                [
+                    {"Num_Min": 2, "Num_Max": 91, "Start_Date_Year": 2030},
+                    {"Num_Min": 0, "Num_Max": 10, "Start_Date_Year": 2031},
+                ],
+                [0.39933993399339934, 0.9999179184109004],
+            ),
+        ],
+    )
+    def test_calc_similarity(self, gold_instance, sys_list, expected):
+        matcher = SpecificInstanceMatcher()
+        if expected:
+            assert matcher.calc_similarity(gold_instance, sys_list) == expected
+        else:
+            with pytest.raises(UnboundLocalError):
+                matcher.calc_similarity(gold_instance, sys_list)
+
+    @pytest.mark.parametrize(
+        "test_gold_list, test_sys_list, expected_gold, expected_sys",
+        [
+            (
+                # gold_list
+                [
+                    {
+                        "Event_ID": "aA3",
+                        "Num_Min": 2,
+                        "Num_Max": 82,
+                        "Start_Date_Year": 2030,
+                        "Location_Norm": ["Amman", "Zarqa"],
+                    },
+                    {
+                        "Event_ID": "aA3",
+                        "Num_Min": None,
+                        "Num_Max": 91,
+                        "Start_Date_Year": 2030,
+                        "Location_Norm": ["Uppsala", "Stockholm"],
+                    },
+                    {
+                        "Event_ID": "aA3",
+                        "Num_Min": 0,
+                        "Num_Max": 10,
+                        "Start_Date_Year": 2031,
+                        "Location_Norm": ["Paris", "Lyon"],
+                    },
+                ],
+                # sys_list
+                [
+                    {
+                        "Event_ID": "aA3",
+                        "Num_Min": 0,
+                        "Num_Max": 11,
+                        "Start_Date_Year": 2031,
+                        "Location_Norm": ["Lyon"],
+                    },
+                    {
+                        "Event_ID": "aA3",
+                        "Num_Min": 1,
+                        "Num_Max": 84,
+                        "Start_Date_Year": 2029,
+                        "Location_Norm": ["Uppsala", "Zarqa"],
+                    },
+                    {
+                        "Event_ID": "aA3",
+                        "Num_Min": 2,
+                        "Num_Max": 91,
+                        "Start_Date_Year": 2030,
+                        "Location_Norm": ["Stockholm"],
+                    },
+                    {
+                        "Event_ID": "aA3",
+                        "Num_Min": 7,
+                        "Num_Max": 30,
+                        "Start_Date_Year": 2030,
+                        "Location_Norm": ["Uppsala", "Linköping"],
+                    },
+                ],
+                # gold
+                [
+                    {
+                        "Event_ID": "aA3-0",
+                        "Num_Min": 0,
+                        "Num_Max": 10,
+                        "Start_Date_Year": 2031,
+                        "Location_Norm": ["Paris", "Lyon"],
+                    },
+                    {
+                        "Event_ID": "aA3-1",
+                        "Num_Min": None,
+                        "Num_Max": 91,
+                        "Start_Date_Year": 2030,
+                        "Location_Norm": ["Uppsala", "Stockholm"],
+                    },
+                    {
+                        "Event_ID": "aA3-2",
+                        "Num_Min": 2,
+                        "Num_Max": 82,
+                        "Start_Date_Year": 2030,
+                        "Location_Norm": ["Amman", "Zarqa"],
+                    },
+                    {
+                        "Event_ID": "aA3-3",
+                        "Num_Min": None,
+                        "Num_Max": None,
+                        "Start_Date_Year": None,
+                        "Location_Norm": None,
+                    },
+                ],
+                # sys
+                [
+                    {
+                        "Event_ID": "aA3-0",
+                        "Num_Min": 0,
+                        "Num_Max": 11,
+                        "Start_Date_Year": 2031,
+                        "Location_Norm": ["Lyon"],
+                    },
+                    {
+                        "Event_ID": "aA3-1",
+                        "Num_Min": 2,
+                        "Num_Max": 91,
+                        "Start_Date_Year": 2030,
+                        "Location_Norm": ["Stockholm"],
+                    },
+                    {
+                        "Event_ID": "aA3-2",
+                        "Num_Min": 1,
+                        "Num_Max": 84,
+                        "Start_Date_Year": 2029,
+                        "Location_Norm": ["Uppsala", "Zarqa"],
+                    },
+                    {
+                        "Event_ID": "aA3-3",
+                        "Num_Min": 7,
+                        "Num_Max": 30,
+                        "Start_Date_Year": 2030,
+                        "Location_Norm": ["Uppsala", "Linköping"],
+                    },
+                ],
+            ),
+            (
+                [{"Event_ID": "aA3", "Num_Min": 1}],
+                [{"Event_ID": "aA3", "Num_Min": 1000}],
+                [
+                    {"Event_ID": "aA3-0", "Num_Min": 1},
+                    {"Event_ID": "aA3-1", "Num_Min": None},
+                ],
+                [
+                    {"Event_ID": "aA3-0", "Num_Min": None},
+                    {"Event_ID": "aA3-1", "Num_Min": 1000},
+                ],
+            ),
+            # empty lists as input
+            ([], [], [], []),
+            # empty sys_list as input
+            (
+                [{"Event_ID": "aA3B4", "Start_Date_Year": 2030}],
+                [],
+                [{"Event_ID": "aA3B4-0", "Start_Date_Year": 2030}],
+                [{"Event_ID": "aA3B4-0", "Start_Date_Year": None}],
+            ),
+            # empty gold_list as input
+            (
+                [],
+                [{"Event_ID": "aA3C4", "Start_Date_Year": 2030}],
+                [{"Event_ID": "aA3C4-0", "Start_Date_Year": None}],
+                [{"Event_ID": "aA3C4-0", "Start_Date_Year": 2030}],
+            ),
+            # inconsistent schema
+            (
+                [
+                    {
+                        "Event_ID": "aA3",
+                        "Num_Min": 0,
+                        "Num_Max": 10,
+                        "Start_Date_Year": 2030,
+                    }
+                ],
+                [
+                    {
+                        "Event_ID": "aA3-0",
+                        "Num_Mix": 2,
+                        "Num_Max": 91,
+                        "Start_Date_Year": 2030,
+                    },
+                    {
+                        "Event_ID": "aA3-1",
+                        "Num_Min": 0,
+                        "Num_Max": 10,
+                        "Start_Date_Year": 2031,
+                    },
+                ],
+                None,
+                None,
+            ),
+        ],
+    )
+    def test_matcher(self, test_gold_list, test_sys_list, expected_gold, expected_sys):
+        matcher = SpecificInstanceMatcher(threshold=0.6, null_penalty=0.5)
+        if expected_gold is not None and expected_sys is not None:
+            assert matcher.match(gold_list=test_gold_list, sys_list=test_sys_list) == (
+                expected_gold,
+                expected_sys,
+            )
+        else:
+            with pytest.raises(BaseException):
+                matcher.match(test_gold_list, test_sys_list)