diff --git a/fastembed/rerank/cross_encoder/onnx_text_cross_encoder.py b/fastembed/rerank/cross_encoder/onnx_text_cross_encoder.py
index 2123155..679f289 100644
--- a/fastembed/rerank/cross_encoder/onnx_text_cross_encoder.py
+++ b/fastembed/rerank/cross_encoder/onnx_text_cross_encoder.py
@@ -56,7 +56,7 @@ supported_onnx_models: list[BaseModelDescription] = [
     ),
     BaseModelDescription(
         model="jinaai/jina-reranker-v2-base-multilingual",
-        description="A multi-lingual reranker model for cross-encoder re-ranking with 1K context length and sliding window",
+        description="A multi-lingual reranker model for cross-encoder re-ranking with 1K context length",
         license="cc-by-nc-4.0",
         size_in_GB=1.11,
         sources=ModelSource(hf="jinaai/jina-reranker-v2-base-multilingual"),
diff --git a/fastembed/text/multitask_embedding.py b/fastembed/text/multitask_embedding.py
index 73ce2b1..2db6813 100644
--- a/fastembed/text/multitask_embedding.py
+++ b/fastembed/text/multitask_embedding.py
@@ -22,7 +22,7 @@ supported_multitask_models: list[DenseModelDescription] = [
         },
         description=(
             "Multi-task unimodal (text) embedding model, multi-lingual (~100), "
-            "1024 tokens truncation, and 8192 sequence length. Prefixes for queries/documents: not necessary, 2024 year."
+            "8192 input tokens truncation. Prefixes for queries/documents: not necessary, 2024 year."
         ),
         license="cc-by-nc-4.0",
         size_in_GB=2.29,
diff --git a/fastembed/text/pooled_embedding.py b/fastembed/text/pooled_embedding.py
index ba9a26a..8e7b65c 100644
--- a/fastembed/text/pooled_embedding.py
+++ b/fastembed/text/pooled_embedding.py
@@ -50,7 +50,7 @@ supported_pooled_models: list[DenseModelDescription] = [
         model="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
         dim=384,
         description=(
-            "Text embeddings, Unimodal (text), Multilingual (~50 languages), 512 input tokens truncation, "
+            "Text embeddings, Unimodal (text), Multilingual (~50 languages), 128 input tokens truncation, "
             "Prefixes for queries/documents: not necessary, 2019 year."
         ),
         license="apache-2.0",
@@ -62,7 +62,7 @@ supported_pooled_models: list[DenseModelDescription] = [
         model="sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
         dim=768,
         description=(
-            "Text embeddings, Unimodal (text), Multilingual (~50 languages), 384 input tokens truncation, "
+            "Text embeddings, Unimodal (text), Multilingual (~50 languages), 512 input tokens truncation, "
             "Prefixes for queries/documents: not necessary, 2021 year."
         ),
         license="apache-2.0",