From e89654d435ed6da99f6538215327dcbcd0adc697 Mon Sep 17 00:00:00 2001 From: Dmitrii Ogn Date: Tue, 24 Dec 2024 17:10:16 +0300 Subject: [PATCH] Hf sources (#429) * HF sources for all models --- fastembed/text/onnx_embedding.py | 3 +++ fastembed/text/onnx_text_model.py | 1 - 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/fastembed/text/onnx_embedding.py b/fastembed/text/onnx_embedding.py index e4d657c7..48b93dae 100644 --- a/fastembed/text/onnx_embedding.py +++ b/fastembed/text/onnx_embedding.py @@ -16,6 +16,7 @@ "license": "mit", "size_in_GB": 0.42, "sources": { + "hf": "Qdrant/fast-bge-base-en", "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en.tar.gz", }, "model_file": "model_optimized.onnx", @@ -50,6 +51,7 @@ "license": "mit", "size_in_GB": 0.13, "sources": { + "hf": "Qdrant/bge-small-en", "url": "https://storage.googleapis.com/qdrant-fastembed/BAAI-bge-small-en.tar.gz", }, "model_file": "model_optimized.onnx", @@ -72,6 +74,7 @@ "license": "mit", "size_in_GB": 0.09, "sources": { + "hf": "Qdrant/bge-small-zh-v1.5", "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-zh-v1.5.tar.gz", }, "model_file": "model_optimized.onnx", diff --git a/fastembed/text/onnx_text_model.py b/fastembed/text/onnx_text_model.py index 95301985..ba3e1516 100644 --- a/fastembed/text/onnx_text_model.py +++ b/fastembed/text/onnx_text_model.py @@ -79,7 +79,6 @@ def onnx_embed( onnx_input["token_type_ids"] = np.array( [np.zeros(len(e), dtype=np.int64) for e in input_ids], dtype=np.int64 ) - onnx_input = self._preprocess_onnx_input(onnx_input, **kwargs) model_output = self.model.run(self.ONNX_OUTPUT_NAMES, onnx_input)