Downloads · 30 days
41
3% of all-time downloads
JJTsao/fine-tuned_movie_retriever-all-mpnet-base-v2
fine-tuned_movie_retriever-all-mpnet-base-v2 is a feature extraction model from JJTsao. Use it when you need embeddings to search or compare text. It is set up for sentence-transformers. The card lists the license as apache-2.0.
[](https://huggingface.co/your-username/my-st-model)
Downloads · 30 days
41
3% of all-time downloads
All-time downloads
1.2K
Public
Parameters
109M
438 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors438 MB · 100%
From the Hugging Face model README
This is a custom fine-tuned sentence-transformer model designed for movie and TV recommendation systems. Optimized for high-quality vector retrieval in a movie and TV show recommendation RAG pipeline. Fine-tuning was done using ~32K synthetic natural language queries across metadata and vibe-based prompts:
BAAI/bge-base-en-v1.5MultipleNegativesRankingLoss| Metric | Fine-Tuned Model Score | Base Model Score |
|---|---|---|
| Recall@1 | 0.459 | 0.159 |
| Recall@3 | 0.695 | 0.289 |
| Recall@5 | 0.765 | 0.342 |
| Recall@10 | 0.836 | 0.425 |
| MRR | 0.598 | 0.251 |
Evaluation setup:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("jjtsao/fine-tuned_movie_retriever-all-mpnet-base-v2")
query_embedding = model.encode("mind-bending sci-fi thrillers from the 2000s about identity")
Apache 2.0 — open for personal and commercial use.