Feature Extraction
sentence-transformers
Safetensors
Korean
distilbert
sentence-similarity
patent
korean
text-embeddings-inference
Instructions to use eunbie/patent-model-success with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use eunbie/patent-model-success with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("eunbie/patent-model-success") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Patent Model Success
ํนํ ๋ฌธ์ ๊ฒ์์ ์ํด fine-tuning๋ ํ๊ตญ์ด sentence-transformer ๋ชจ๋ธ์ ๋๋ค.
๋ชจ๋ธ ์ ๋ณด
- Base Model: distiluse-base-multilingual-cased-v2
- Training Data: 30๊ฐ ํ๊ตญ์ด ํนํ ๋ฌธ์ ์
- Loss Function: MultipleNegativesRankingLoss
- Use Case: ํนํ ๋ฌธ์ ์ ์ฌ๋ ๊ฒ์, RAG ์์คํ
์ฌ์ฉ ๋ฐฉ๋ฒ
from sentence_transformers import SentenceTransformer
# ๋ชจ๋ธ ๋ก๋
model = SentenceTransformer("eunbie/patent-model-success")
# ๋ฌธ์ฅ ์๋ฒ ๋ฉ
sentences = ["๋ธ๋ก์ฒด์ธ ๊ธฐ๋ฐ ํนํ ๊ด๋ฆฌ ์์คํ
", "AI ํนํ ๊ฒ์ ์์คํ
"]
embeddings = model.encode(sentences)
# ์ ์ฌ๋ ๊ณ์ฐ
from sentence_transformers.util import cos_sim
similarity = cos_sim(embeddings[0], embeddings[1])
ํ๋ก์ ํธ
์ด ๋ชจ๋ธ์ Patent Chat AI ํ๋ก์ ํธ์ ์ผ๋ถ์ ๋๋ค.
๋ผ์ด์ ์ค
Apache 2.0
- Downloads last month
- 17