Upload embedding.py

embedding.py

@@ -0,0 +1,20 @@
+from sentence_transformers import SentenceTransformer
+from preprocess import meme_attribute, meme_filename, meme_list
+# This model supports two prompts: "s2p_query" and "s2s_query" for sentence-to-passage and sentence-to-sentence tasks, respectively.
+# They are defined in `config_sentence_transformers.json`
+
+
+# you can also use this model without the features of `use_memory_efficient_attention` and `unpad_inputs`. It can be worked in CPU.
+model = SentenceTransformer(
+     "dunzhang/stella_en_400M_v5",
+     trust_remote_code=True,
+     device="cpu",
+     config_kwargs={"use_memory_efficient_attention": False, "unpad_inputs": False}
+)
+
+docs_list = list(meme_attribute.values())
+
+doc_embeddings = model.encode(docs_list)
+
+embedded_dict = {key: embedding for key, embedding in zip(meme_attribute.keys(), doc_embeddings)}
+