From bb8c69eadec589b40221d14c87cc57efd71261e1 Mon Sep 17 00:00:00 2001 From: George Panchuk Date: Mon, 28 Sep 2026 20:00:57 +0700 Subject: [PATCH] fix: fix description limits --- fastembed/rerank/cross_encoder/onnx_text_cross_encoder.py | 2 +- fastembed/text/multitask_embedding.py | 2 +- fastembed/text/pooled_embedding.py | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/fastembed/rerank/cross_encoder/onnx_text_cross_encoder.py b/fastembed/rerank/cross_encoder/onnx_text_cross_encoder.py index 212315513..679f289e4 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 @@ ), 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 73ce2b1bd..2db6813e4 100644 --- a/fastembed/text/multitask_embedding.py +++ b/fastembed/text/multitask_embedding.py @@ -22,7 +22,7 @@ }, 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 ba9a26a21..8e7b65c9a 100644 --- a/fastembed/text/pooled_embedding.py +++ b/fastembed/text/pooled_embedding.py @@ -50,7 +50,7 @@ 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 @@ 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",