Sentence Similarity
sentence-transformers
Safetensors
English
Chinese
code
xlm-roberta
feature-extraction
mathlib4
lean4
formal-proof
retrieval
code-retrieval
math
text-embeddings-inference
Instructions to use YuxuanGong/lean-RAG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use YuxuanGong/lean-RAG with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("YuxuanGong/lean-RAG") sentences = [ "theorem length_take_of_le_length | (s.take n).length = n", "Keywords: less than or equal find if and only natural number lemma proposition | Name: Nat le_find_iff | Kind: lemma | Namespace: Nat", "Keywords: length take le' list theorem proposition | Name: List length_take_le' | Kind: theorem | Namespace: List", "Keywords: take length list theorem proposition | Name: List take_length | Kind: theorem | Namespace: List" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 1f31e6b961911e555a6724d9c5b6c757077ef76fcc47400b1ec636e631af9f70
- Size of remote file:
- 17.1 MB
- SHA256:
- 186958617870145e2384b91f3e26e0299499ee25baba7b72c7a761e16641e797
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.