EuroEval 15.10.0__tar.gz → 15.10.1__tar.gz

{euroeval-15.10.0 → euroeval-15.10.1}/.pre-commit-config.yaml

@@ -10,7 +10,7 @@ repos:
       - id: trailing-whitespace
       - id: debug-statements
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.13
+    rev: v0.12.0
     hooks:
       - id: ruff
         args:

{euroeval-15.10.0 → euroeval-15.10.1}/CHANGELOG.md

@@ -10,6 +10,12 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 
 
 
+## [v15.10.1] - 2025-06-20
+### Fixed
+- Fixed an issue when benchmarking encoder models on reading comprehension tasks, where
+  we sometimes would truncate the model outputs when they should not have been.
+
+
 ## [v15.10.0] - 2025-06-17
 ### Changed
 - Updated `vllm` to `>=0.9.1`.

{euroeval-15.10.0 → euroeval-15.10.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: EuroEval
-Version: 15.10.0
+Version: 15.10.1
 Summary: The robust European language model benchmark.
 Project-URL: Repository, https://github.com/EuroEval/EuroEval
 Project-URL: Issues, https://github.com/EuroEval/EuroEval/issues

{euroeval-15.10.0 → euroeval-15.10.1}/docs/README.md

@@ -29,7 +29,7 @@ or [LM Studio](https://lmstudio.ai/).
 The idea of EuroEval grew out of the development of Danish language model RøBÆRTa in
 2021, when we realised that there was no standard way to evaluate Danish language
 models. It started as a hobby project including Danish, Swedish and Norwegian, but has
-since grown to include 8+ European languages.
+since grown to include 12+ European languages.
 
 EuroEval is maintained by [Dan Saattrup Nielsen](https://www.saattrupdan.com/) from the
 [Alexandra Institute](https://alexandra.dk), and is funded by the EU project

euroeval-15.10.1/docs/leaderboards/Monolingual/finnish.md

@@ -0,0 +1,15 @@
+---
+hide:
+    - toc
+---
+# 🇫🇮 Finnish
+
+See the [leaderboard page](/leaderboards) for more information about all the columns.
+
+/// tab | Generative Leaderboard
+<iframe title="" aria-label="Table" id="datawrapper-chart-ubHSy" src="https://datawrapper.dwcdn.net/ubHSy" scrolling="no" frameborder="0" style="width: 0; min-width: 100% !important; border: none;" height="847" data-external="1"></iframe><script type="text/javascript">!function(){"use strict";window.addEventListener("message",(function(a){if(void 0!==a.data["datawrapper-height"]){var e=document.querySelectorAll("iframe");for(var t in a.data["datawrapper-height"])for(var r,i=0;r=e[i];i++)if(r.contentWindow===a.source){var d=a.data["datawrapper-height"][t]+"px";r.style.height=d}}}))}();</script>
+///
+
+/// tab | NLU Leaderboard
+<iframe title="" aria-label="Table" id="datawrapper-chart-qVbA3" src="https://datawrapper.dwcdn.net/qVbA3/1/" scrolling="no" frameborder="0" style="width: 0; min-width: 100% !important; border: none;" height="818" data-external="1"></iframe><script type="text/javascript">!function(){"use strict";window.addEventListener("message",(function(a){if(void 0!==a.data["datawrapper-height"]){var e=document.querySelectorAll("iframe");for(var t in a.data["datawrapper-height"])for(var r,i=0;r=e[i];i++)if(r.contentWindow===a.source){var d=a.data["datawrapper-height"][t]+"px";r.style.height=d}}}))}();</script>
+///

{euroeval-15.10.0 → euroeval-15.10.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "EuroEval"
-version = "15.10.0"
+version = "15.10.1"
 description = "The robust European language model benchmark."
 readme = "README.md"
 authors = [

{euroeval-15.10.0 → euroeval-15.10.1}/src/euroeval/finetuning.py

@@ -333,7 +333,7 @@ def remove_extra_tensors_from_logits(
     Returns:
         The processed logits.
     """
-    if isinstance(logits, tuple):
+    if isinstance(logits, tuple) and isinstance(logits[-1], tuple):
         logits = logits[:-1]
         if len(logits) == 1:
             logits = logits[0]

{euroeval-15.10.0 → euroeval-15.10.1}/uv.lock

@@ -928,7 +928,7 @@ wheels = [
 
 [[package]]
 name = "euroeval"
-version = "15.10.0"
+version = "15.10.1"
 source = { editable = "." }
 dependencies = [
     { name = "accelerate" },