Instructions to use Suf7/resumatch-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Suf7/resumatch-models with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Suf7/resumatch-models") 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
Resumatch models (Deliverable 2)
Fine-tuned MiniLM-L6 bi-encoder and MatchNet reranker for the Resumatch AI semester project (FAST-NUCES Lahore).
Contents
| Path | What |
|---|---|
bi_encoder/ |
all-MiniLM-L6-v2 fine-tuned with multiple-negatives ranking loss (sentence-transformers format) |
matchnet_weak.pt |
MatchNet trained on our occupation-level pairs (state dict, config, feature scaler) |
matchnet_human.pt |
MatchNet trained on human-labelled fit pairs |
Load
# from the Resumatch repo
make weights
or
from huggingface_hub import snapshot_download
snapshot_download("Suf7/resumatch-models", local_dir="models",
allow_patterns=["bi_encoder/**", "matchnet_*.pt"])
Code, training, metrics and the report: https://github.com/Suf-7/Resumatch
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support