EuroEval 15.16.0__py3-none-any.whl → 16.0.1__py3-none-any.whl

euroeval/utils.py

@@ -8,12 +8,15 @@ import importlib.util
 import logging
 import os
 import random
+import re
 import sys
 import typing as t
 import warnings
 from functools import cache
 from pathlib import Path
 
+import demjson3
+import huggingface_hub as hf_hub
 import litellm
 import numpy as np
 import requests
@@ -22,10 +25,7 @@ from datasets.utils import disable_progress_bar
 from requests.exceptions import RequestException
 from transformers import logging as tf_logging
 
-from .exceptions import NaNValueInModelOutput
-
-if importlib.util.find_spec("ray") is not None:
-    import ray
+from .exceptions import InvalidBenchmark, NaNValueInModelOutput
 
 if t.TYPE_CHECKING:
     from types import TracebackType
@@ -94,54 +94,53 @@ def block_terminal_output() -> None:
     # Ignore miscellaneous warnings
     warnings.filterwarnings("ignore", category=UserWarning)
     warnings.filterwarnings("ignore", category=FutureWarning)
-    warnings.filterwarnings(
-        "ignore",
-        module="torch.nn.parallel*",
-        message="Was asked to gather along dimension 0, but all input tensors were "
-        "scalars; will instead unsqueeze and return a vector.",
-    )
-    warnings.filterwarnings("ignore", module="seqeval*")
-
-    # Up the logging level, to disable outputs
-    logging.getLogger("filelock").setLevel(logging.CRITICAL)
     logging.getLogger("absl").setLevel(logging.CRITICAL)
-    logging.getLogger("datasets").setLevel(logging.CRITICAL)
+
+    # Disable matplotlib logging
+    logging.getLogger("matplotlib.font_manager").setLevel(logging.CRITICAL)
+
+    # Disable PyTorch logging
+    logging.getLogger("torch.utils.cpp_extension").setLevel(logging.CRITICAL)
+    warnings.filterwarnings(action="ignore", module="torch*")
+    os.environ["TORCH_LOGS"] = "-all"
+
+    # Disable huggingface_hub logging
+    logging.getLogger("huggingface_hub").setLevel(logging.CRITICAL)
+
+    # Disable LiteLLM logging
+    logging.getLogger("LiteLLM").setLevel(logging.CRITICAL)
+    logging.getLogger("LiteLLM Router").setLevel(logging.CRITICAL)
+    logging.getLogger("LiteLLM Proxy").setLevel(logging.CRITICAL)
     logging.getLogger("openai").setLevel(logging.CRITICAL)
-    logging.getLogger("torch.distributed.distributed_c10d").setLevel(logging.CRITICAL)
-    logging.getLogger("torch.nn.parallel.distributed").setLevel(logging.CRITICAL)
+    logging.getLogger("httpx").setLevel(logging.CRITICAL)
+    litellm.suppress_debug_info = True
+
+    # Disable vLLM logging
     logging.getLogger("vllm").setLevel(logging.CRITICAL)
     logging.getLogger("vllm.engine.llm_engine").setLevel(logging.CRITICAL)
     logging.getLogger("vllm.transformers_utils.tokenizer").setLevel(logging.CRITICAL)
     logging.getLogger("vllm.core.scheduler").setLevel(logging.CRITICAL)
     logging.getLogger("vllm.model_executor.weight_utils").setLevel(logging.CRITICAL)
     logging.getLogger("vllm.platforms").setLevel(logging.CRITICAL)
-    logging.getLogger("httpx").setLevel(logging.CRITICAL)
-    logging.getLogger("ray._private.worker").setLevel(logging.CRITICAL)
-    logging.getLogger("ray._private.services").setLevel(logging.CRITICAL)
-    logging.getLogger("matplotlib.font_manager").setLevel(logging.CRITICAL)
-    logging.getLogger("accelerate").setLevel(logging.CRITICAL)
-    logging.getLogger("LiteLLM").setLevel(logging.CRITICAL)
-    logging.getLogger("LiteLLM Router").setLevel(logging.CRITICAL)
-    logging.getLogger("LiteLLM Proxy").setLevel(logging.CRITICAL)
-    logging.getLogger("huggingface_hub").setLevel(logging.CRITICAL)
-
-    # This suppresses vLLM logging
+    logging.getLogger("mistral_common.tokens.tokenizers.tekken").setLevel(
+        logging.CRITICAL
+    )
     os.environ["LOG_LEVEL"] = "CRITICAL"
     os.environ["VLLM_CONFIGURE_LOGGING"] = "0"
 
-    if importlib.util.find_spec("ray") is not None:
-        ray._private.worker._worker_logs_enabled = False
-
-    # Disable the tokeniser progress bars
+    # Disable datasets logging
+    logging.getLogger("datasets").setLevel(logging.CRITICAL)
+    logging.getLogger("filelock").setLevel(logging.CRITICAL)
     disable_progress_bar()
 
+    # Disable evaluate logging
+    warnings.filterwarnings("ignore", module="seqeval*")
+
     # Disable most of the `transformers` logging
     tf_logging._default_log_level = logging.CRITICAL
     tf_logging.set_verbosity(logging.CRITICAL)
     logging.getLogger("transformers.trainer").setLevel(logging.CRITICAL)
-
-    # Disable logging from `litellm`
-    litellm.suppress_debug_info = True
+    logging.getLogger("accelerate").setLevel(logging.CRITICAL)
 
 
 def get_class_by_name(class_name: str | list[str], module_name: str) -> t.Type | None:
@@ -373,3 +372,119 @@ async def add_semaphore_and_catch_exception(
             return await coroutine
         except Exception as exc:
             return exc
+
+
+def extract_json_dict_from_string(s: str) -> dict | None:
+    """Extract a JSON dictionary from a string.
+
+    Args:
+        s:
+            The string to extract the JSON dictionary from.
+
+    Returns:
+        The extracted JSON dictionary, or None if no JSON dictionary could be found.
+    """
+    json_regex = r"\{[^{}]+?\}"
+    if (json_match := re.search(pattern=json_regex, string=s, flags=re.DOTALL)) is None:
+        logger.debug(
+            "The model output does not contain any JSON dictionary, so cannot parse "
+            f"it. Skipping. Here is the output: {s!r}"
+        )
+        return None
+    json_string = json_match.group()
+    try:
+        json_output = demjson3.decode(txt=json_string)
+    except demjson3.JSONDecodeError:
+        logger.debug(
+            "The model output is not valid JSON, so cannot parse it. Skipping. "
+            f"Here is the output: {json_string!r}"
+        )
+        return None
+    if not isinstance(json_output, dict):
+        logger.debug(
+            "The model output is not a JSON dictionary, so cannot parse "
+            f"it. Skipping. Here is the output: {json_string!r}"
+        )
+        return None
+    elif not all(isinstance(key, str) for key in json_output.keys()):
+        logger.debug(
+            "The model output is not a JSON dictionary with string keys, "
+            "so cannot parse it. Skipping. Here is the output: "
+            f"{json_string!r}"
+        )
+        return None
+    return json_output
+
+
+@cache
+def get_hf_token(api_key: str | None) -> str | bool:
+    """Get the Hugging Face token.
+
+    Args:
+        api_key:
+            The API key to use as the Hugging Face token. If None, we will try to
+            extract it in other ways.
+
+    Returns:
+        The Hugging Face token, or True if no token is set but the user is logged in, or
+        False if no token is set and the user is not logged in.
+    """
+    if api_key is not None:
+        log_once(
+            "Using the Hugging Face API key passed to the function.",
+            level=logging.DEBUG,
+        )
+        return api_key
+    elif (token := os.getenv("HUGGINGFACE_API_KEY")) is not None:
+        log_once(
+            "Using the Hugging Face API key from the environment variable "
+            "`HUGGINGFACE_API_KEY`.",
+            level=logging.DEBUG,
+        )
+        return token
+    try:
+        hf_hub.whoami()
+        log_once(
+            "No Hugging Face API key was set, but the user is logged in to Hugging "
+            "Face, so using the local token.",
+            level=logging.DEBUG,
+        )
+        return True
+    except hf_hub.errors.LocalTokenNotFoundError:
+        log_once(
+            "No Hugging Face API key was set and the user is not logged in to Hugging "
+            "Face, so no token will be used.",
+            level=logging.DEBUG,
+        )
+        return False
+
+
+def extract_multiple_choice_labels(
+    prompt: str, candidate_labels: list[str]
+) -> list[str]:
+    """Extract multiple choice labels from a prompt.
+
+    Args:
+        prompt:
+            The prompt to extract the labels from.
+        candidate_labels:
+            The candidate labels to look for in the prompt.
+
+    Returns:
+        The extracted labels.
+    """
+    sample_candidate_labels: list[str] = list()
+    for candidate_label in candidate_labels:
+        candidate_label_match = re.search(
+            pattern=rf"\b{candidate_label}\. ", string=prompt, flags=re.IGNORECASE
+        )
+        if candidate_label_match is not None:
+            sample_candidate_labels.append(candidate_label)
+    if not sample_candidate_labels:
+        raise InvalidBenchmark(
+            "Could not extract any candidate labels from the prompt. Please ensure "
+            "that the candidate labels are present in the prompt, each followed by a "
+            "dot and a space (e.g., 'a. '). The candidate labels are: "
+            f"{', '.join(candidate_labels)}. Here is the prompt: {prompt!r}"
+        )
+    return sample_candidate_labels

{euroeval-15.16.0.dist-info → euroeval-16.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: EuroEval
-Version: 15.16.0
+Version: 16.0.1
 Summary: The robust European language model benchmark.
 Project-URL: Repository, https://github.com/EuroEval/EuroEval
 Project-URL: Issues, https://github.com/EuroEval/EuroEval/issues
@@ -28,18 +28,19 @@ License: MIT License
         OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
         SOFTWARE.
 License-File: LICENSE
-Requires-Python: <4.0,>=3.10
+Requires-Python: <4.0,>=3.11
 Requires-Dist: accelerate>=1.9.0
 Requires-Dist: bert-score>=0.3.13
 Requires-Dist: click>=8.1.3
+Requires-Dist: cloudpickle>=3.1.1
 Requires-Dist: datasets>=3.5.0
 Requires-Dist: demjson3>=3.0.6
 Requires-Dist: evaluate>=0.4.1
 Requires-Dist: huggingface-hub>=0.30.1
 Requires-Dist: levenshtein>=0.24.0
-Requires-Dist: litellm>=1.72.2
+Requires-Dist: litellm>=1.75.6
 Requires-Dist: more-itertools>=10.5.0
-Requires-Dist: numpy<2.0.0,>=1.23.0
+Requires-Dist: numpy>=2.0.0
 Requires-Dist: ollama>=0.5.1
 Requires-Dist: pandas>=2.2.0
 Requires-Dist: peft>=0.15.0
@@ -49,27 +50,24 @@ Requires-Dist: pyinfer>=0.0.3
 Requires-Dist: python-dotenv>=1.0.1
 Requires-Dist: rouge-score>=0.1.2
 Requires-Dist: sacremoses>=0.1.1
-Requires-Dist: scikit-learn<1.6.0
+Requires-Dist: scikit-learn==1.6.1
 Requires-Dist: sentencepiece>=0.1.96
 Requires-Dist: seqeval>=1.2.2
 Requires-Dist: setuptools>=75.8.2
 Requires-Dist: tenacity>=9.0.0
 Requires-Dist: termcolor>=2.0.0
 Requires-Dist: torch>=2.6.0
-Requires-Dist: transformers>=4.55.0
+Requires-Dist: transformers[mistral-common]>=4.56.0
 Provides-Extra: all
 Requires-Dist: bitsandbytes>=0.43.1; (platform_system == 'Linux') and extra == 'all'
 Requires-Dist: fbgemm-gpu>=1.0.0; (platform_system == 'Linux') and extra == 'all'
-Requires-Dist: gradio>=4.26.0; extra == 'all'
-Requires-Dist: vllm>=0.10.0; (platform_system == 'Linux') and extra == 'all'
+Requires-Dist: flashinfer-python>=0.3.1; (platform_system == 'Linux') and extra == 'all'
+Requires-Dist: vllm>=0.10.1; (platform_system == 'Linux') and extra == 'all'
 Provides-Extra: generative
 Requires-Dist: bitsandbytes>=0.43.1; (platform_system == 'Linux') and extra == 'generative'
 Requires-Dist: fbgemm-gpu>=1.0.0; (platform_system == 'Linux') and extra == 'generative'
-Requires-Dist: vllm>=0.10.0; (platform_system == 'Linux') and extra == 'generative'
-Provides-Extra: human-evaluation
-Requires-Dist: gradio>=4.26.0; extra == 'human-evaluation'
-Provides-Extra: test
-Requires-Dist: gradio>=4.26.0; extra == 'test'
+Requires-Dist: flashinfer-python>=0.3.1; (platform_system == 'Linux') and extra == 'generative'
+Requires-Dist: vllm>=0.10.1; (platform_system == 'Linux') and extra == 'generative'
 Description-Content-Type: text/markdown
 
 <div align='center'>
@@ -223,17 +221,18 @@ A huge thank you to all the contributors who have helped make this project a suc
 <a href="https://github.com/AJDERS"><img src="https://avatars.githubusercontent.com/u/38854604" width=50 alt="Contributor avatar for AJDERS"/></a>
 <a href="https://github.com/oliverkinch"><img src="https://avatars.githubusercontent.com/u/71556498" width=50 alt="Contributor avatar for oliverkinch"/></a>
 <a href="https://github.com/versae"><img src="https://avatars.githubusercontent.com/u/173537" width=50 alt="Contributor avatar for versae"/></a>
+<a href="https://github.com/KennethEnevoldsen"><img src="https://avatars.githubusercontent.com/u/23721977" width=50 alt="Contributor avatar for KennethEnevoldsen"/></a>
 <a href="https://github.com/viggo-gascou"><img src="https://avatars.githubusercontent.com/u/94069687" width=50 alt="Contributor avatar for viggo-gascou"/></a>
 <a href="https://github.com/mathiasesn"><img src="https://avatars.githubusercontent.com/u/27091759" width=50 alt="Contributor avatar for mathiasesn"/></a>
 <a href="https://github.com/Alkarex"><img src="https://avatars.githubusercontent.com/u/1008324" width=50 alt="Contributor avatar for Alkarex"/></a>
 <a href="https://github.com/marksverdhei"><img src="https://avatars.githubusercontent.com/u/46672778" width=50 alt="Contributor avatar for marksverdhei"/></a>
 <a href="https://github.com/Mikeriess"><img src="https://avatars.githubusercontent.com/u/19728563" width=50 alt="Contributor avatar for Mikeriess"/></a>
-<a href="https://github.com/pakagronglb"><img src="https://avatars.githubusercontent.com/u/178713124" width=50 alt="Contributor avatar for pakagronglb"/></a>
 <a href="https://github.com/ThomasKluiters"><img src="https://avatars.githubusercontent.com/u/8137941" width=50 alt="Contributor avatar for ThomasKluiters"/></a>
 <a href="https://github.com/BramVanroy"><img src="https://avatars.githubusercontent.com/u/2779410" width=50 alt="Contributor avatar for BramVanroy"/></a>
 <a href="https://github.com/peregilk"><img src="https://avatars.githubusercontent.com/u/9079808" width=50 alt="Contributor avatar for peregilk"/></a>
 <a href="https://github.com/Rijgersberg"><img src="https://avatars.githubusercontent.com/u/8604946" width=50 alt="Contributor avatar for Rijgersberg"/></a>
 <a href="https://github.com/duarteocarmo"><img src="https://avatars.githubusercontent.com/u/26342344" width=50 alt="Contributor avatar for duarteocarmo"/></a>
+<a href="https://github.com/slowwavesleep"><img src="https://avatars.githubusercontent.com/u/44175589" width=50 alt="Contributor avatar for slowwavesleep"/></a>
 
 
 ### Contribute to EuroEval

euroeval-16.0.1.dist-info/RECORD

@@ -0,0 +1,69 @@
+euroeval/__init__.py,sha256=8jqSCcDWvwwNb1guPi8cLAekPSOX9V8DpRx_v3-c19E,3730
+euroeval/benchmark_config_factory.py,sha256=ZKzGkWr-Mr4wEMYNXUHsYkd2R-dxnNyETZJJ-Fq-my0,11386
+euroeval/benchmarker.py,sha256=YNqhl2QchqzbGMGu8QoJAG_mnYbcJ46ksfaS0x78fiw,49847
+euroeval/callbacks.py,sha256=5BTlDvBJ60xRvj01EpXZSZu3MFdKa3LgVuhxoLb3i3E,2565
+euroeval/cli.py,sha256=RR45NiHMI9hphqBJ7Xopde-C18Be9JgJxgg6eYPFVMM,8594
+euroeval/constants.py,sha256=imy-YwofbAwTbjk_vgynYf3zaK5kKV349oXZl99DVyM,2742
+euroeval/data_loading.py,sha256=F3fHyR7FoS_a1dx_DyqtcxdB-jxWwE3RCNRvWcp5z1c,4527
+euroeval/data_models.py,sha256=UGyqPAYFImrR1gi4ctQdCVb0rjVkEmyf4Lc1a7_6t6E,24663
+euroeval/enums.py,sha256=V73E8FTL1aRz74OKcxokTYLnO7Q8HGs2QI0JPZI4qQo,3032
+euroeval/exceptions.py,sha256=5kQ-YvHyFO3aaA-zfOTaS07LRFH8xlSqlOiATvnIObY,5116
+euroeval/finetuning.py,sha256=G86pxxjOAgtcEWpyYDwYOV9pM7WG2Uu9fu7GdDso8dI,11426
+euroeval/generation.py,sha256=wm2u8fDGDgtWxCReG3N6v4_lLvo0OHTpR88ThGSRH7A,12139
+euroeval/generation_utils.py,sha256=w3hfiJfUPDjf2xSKdDrhlpfuxZlztF0_0h2sFPB2hT0,16212
+euroeval/languages.py,sha256=G2cJI8lDT7eOFHxNR9opJ6zWjdxFDwm8P8HY_4WKFI4,33815
+euroeval/model_cache.py,sha256=h61cL_fy2Sd1sqYZis5lAWqvQIfQXXt_v8QZeftKNkg,9226
+euroeval/model_config.py,sha256=64KKHPTrpsFhFAANtBnAKkOs7PWZ50GXkXeDl4jICgs,2748
+euroeval/model_loading.py,sha256=B6dyjYO0Dg7NOcUXls8Sjwe6W0c2UqJ1OGw-RkzoSSQ,2239
+euroeval/scores.py,sha256=gJ7DSQVyE2_8qZxJPuUJcFk7Byj2D7nevE23kd4XMbA,3004
+euroeval/speed_benchmark.py,sha256=3iz_bfJgAoJ9K2HNjufyrBMjHVT8PAjuY_NocBGwKe0,4044
+euroeval/tasks.py,sha256=fwmDKnIexmWbm8HueLUilYzqdNRfo0rFxX-tjZ53Nbg,4503
+euroeval/tokenization_utils.py,sha256=66nip9llPw3XBEzGY0TE1DrejLV2WvdSA1p1euXC6Bg,20556
+euroeval/types.py,sha256=SCKOALV_-F1PAIwQ7qHNdSF1Uy29TSu9nIc1NYJGUUs,2754
+euroeval/utils.py,sha256=ITvT-JxXosrDuElNV7cbASfxzDWSBz9mJWAZHiTOiZY,15304
+euroeval/benchmark_modules/__init__.py,sha256=TNO-sNDwlXE-LMFXfwwqjQqUy55gywSmwRBcoPUFuaU,236
+euroeval/benchmark_modules/base.py,sha256=vYW97bnlzqxxcIq6lY-zd0o6zxyDRMhT85jOhdKnoYE,11482
+euroeval/benchmark_modules/fresh.py,sha256=_iRTHt9qUkq7jPOlgwx7IwZG48dK4mjMrh7KiEHeUjE,10462
+euroeval/benchmark_modules/hf.py,sha256=HDXuVwt0kZUyL9x3aG5pEjSdGCRfzegqT0xKZYprjU0,43843
+euroeval/benchmark_modules/litellm.py,sha256=M6ct5ppcYfO-Il5VMRm3PuyAeQ-rtS22UKyRStLnqfM,59210
+euroeval/benchmark_modules/vllm.py,sha256=ckWLA9maDP5TLAfLhEXzkOYJBngb5BQR7X7RLKPl64A,41824
+euroeval/dataset_configs/__init__.py,sha256=lEOr4kJzgtUymeNBVhd-VwdUK0YTUZ3GjUMlLz5fGWk,2010
+euroeval/dataset_configs/danish.py,sha256=Pb43E-xfgQk9uaxq8ooznvf8okdX8KAYFEPHt1CG_TQ,5192
+euroeval/dataset_configs/dutch.py,sha256=tY7FDw7BmhXxNfI1hqfasxQXP0QbYTqknokTZ7gqdRY,5079
+euroeval/dataset_configs/english.py,sha256=Y4yc3AQu8WojqENj0sy4-rIlx1LhPnsCQ0DeonqDsVs,4128
+euroeval/dataset_configs/estonian.py,sha256=o13P_XkrdhLFCz9l8LJy-TSY3JIN7XmByxesEDiagnc,2879
+euroeval/dataset_configs/faroese.py,sha256=sFC25nwlPtnl6hwkPOxPkwVggPGTjw167YhSBnLl1EA,3039
+euroeval/dataset_configs/finnish.py,sha256=7iXjjpJ23tupvtXwJF3TH1Tzwhxw0RFaoBv38HclsJc,3950
+euroeval/dataset_configs/french.py,sha256=9ofGQpnjw0j_lPB0SuWMvbuWVZXfOvROMqZ03d-EAHs,4281
+euroeval/dataset_configs/german.py,sha256=qsJO2YCND8Kuc_atSWXjkoD2itUQNbUsExiGk7P0OnE,4459
+euroeval/dataset_configs/icelandic.py,sha256=qX-szARxqzJ9l-h0k5iXirC5StpW_B3BOakZQ14zmpM,5797
+euroeval/dataset_configs/italian.py,sha256=xoS_oIFXnTraiV9PX2dBsE1GyodlAbma5dEB7yM_Q8A,4564
+euroeval/dataset_configs/latvian.py,sha256=tibwTbe-atsRZEBbegJ6nbr1Oh4RthUYhZoHPVVawq0,2273
+euroeval/dataset_configs/norwegian.py,sha256=eTX0KpjH60FyLGrUTfspvNvYaL-Ytfw3DTFftlriVM0,7295
+euroeval/dataset_configs/portuguese.py,sha256=x-Idrdo_EtmB_xoabwKivKG091DvFEQEbO6MTcjZVqs,3646
+euroeval/dataset_configs/spanish.py,sha256=5m3Qh328YPhbN8jFPIy9Sa7ZWob02ToCWzlDoT8IsSw,4462
+euroeval/dataset_configs/swedish.py,sha256=j_I7ba9a0nXzEPvpnPTuNFEkS51pnUPrnRwcqGh7tu0,4715
+euroeval/metrics/__init__.py,sha256=qkELjrnBkuO9WzeQJZQRyXpZg_WclUByHswAc6Il7Ns,199
+euroeval/metrics/base.py,sha256=4vnRIPfKUwTNe0ZVm5YC2jQNecwchGUpN6nAH5cX0PM,2288
+euroeval/metrics/huggingface.py,sha256=b_Z_FUELQcmK7HeJh0zlAZs3pim1uNHnFLu7nvlZ4_A,5824
+euroeval/metrics/llm_as_a_judge.py,sha256=YCUHWK3_bkMEYvL7Q79ZAK3V0M1m5rq5zJYdtMxa4fs,9686
+euroeval/metrics/pipeline.py,sha256=a09Um3tnNdyQhzyDa9k-seYQXriYiJRQ5vyHK2lrKcg,10276
+euroeval/metrics/speed.py,sha256=tLna031y0SVzAv6lvXBxf8IOSiw9dvLlonky2zM3MnE,1369
+euroeval/prompt_templates/__init__.py,sha256=HWMZpybxs2xHPnVeJ43893conARahIVLWNXeRhXEGZw,357
+euroeval/prompt_templates/linguistic_acceptability.py,sha256=9ZIyv_hfI2Aj20Uy9SY1izq5OBRV844PXPiZCNCOoEY,8207
+euroeval/prompt_templates/multiple_choice.py,sha256=TCMKB0xS5IEa8f4YEUjsoifcUpaIv4yOL4FisVvPwok,6423
+euroeval/prompt_templates/named_entity_recognition.py,sha256=_ZRVDcnbXvTs_C2NXy78oMbCLFDtW9SuxmvSVg51Umo,15554
+euroeval/prompt_templates/reading_comprehension.py,sha256=eRMN-kCT3wuImbuFXzZYfo5WiVhCFWJkCYwRUDtpeWo,8208
+euroeval/prompt_templates/sentiment_classification.py,sha256=eIXn-aAY7LKeXqxzMKoqdVbihA2f1RaNQk7DhceuQdQ,8887
+euroeval/prompt_templates/summarization.py,sha256=GvnKuYJKbJ_2QkdtSWp_h4RhfOXdq-7_yYeClJSPaTY,6137
+euroeval/task_group_utils/__init__.py,sha256=CorGVkixkoEDOQuDsrOGlTmF1zmM0wnGHs8psWTfD28,72
+euroeval/task_group_utils/multiple_choice_classification.py,sha256=i5sidJGAXnENRoB6pOelyaUeGP1qoxwPSzD-F9RLwWk,7106
+euroeval/task_group_utils/question_answering.py,sha256=vdEbcZy7BE6ICA7kWkPYmPW4eVuIiZ_4uJRLUexDhwY,27750
+euroeval/task_group_utils/sequence_classification.py,sha256=ZIXcYo6ins9VUv8TT4aupWrfUQoWGBlgU8a1hYATOYM,17249
+euroeval/task_group_utils/text_to_text.py,sha256=7f4hGAs5WNJ9PmW1mLhjDMrPxrYAvw5axXsneiJop1w,4993
+euroeval/task_group_utils/token_classification.py,sha256=sNl0rhkXI9g5zKsJujrWX-9jWbYYK2iaKA1AcUg0xW4,17118
+euroeval-16.0.1.dist-info/METADATA,sha256=toyIiyjwyl4Oty2YsD-P6r95hN0Si3BkBNBMOfmiwBA,13729
+euroeval-16.0.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+euroeval-16.0.1.dist-info/entry_points.txt,sha256=-mtBu-10bFWeZ2bS32gVK6-s-LNCQLxvnNUPBLd5ud4,87
+euroeval-16.0.1.dist-info/licenses/LICENSE,sha256=guvz_zBHgkQSY_QiUU0Bkc1k-L_PFZuLjIPfuKne2OY,1080
+euroeval-16.0.1.dist-info/RECORD,,

{euroeval-15.16.0.dist-info → euroeval-16.0.1.dist-info}/entry_points.txt

@@ -1,4 +1,3 @@
 [console_scripts]
 euroeval = euroeval.cli:benchmark
-human_evaluate = euroeval.human_evaluation:main
 scandeval = euroeval.cli:benchmark