Feature Extraction
sentence-transformers
Safetensors
English
auditing
llm
reasoning-tokens
matching-head
Instructions to use s1ghhh/CoIn-Matching-Head with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use s1ghhh/CoIn-Matching-Head with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("s1ghhh/CoIn-Matching-Head") 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
Commit History
-
Update README.md
Verified signature319642d -
Create README.md
Verified signature# CoIn-Matching-Head Pre-trained matching head models for the **CoIn** framework — a system for auditing hidden reasoning tokens in commercial LLM APIs. **Paper**: [CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs](https://arxiv.org/abs/2505.13778) **Code**: [GitHub](https://github.com/s1ghhh/LLM-Auditing-CoIn) ## Model Description This repository contains three pre-trained models used in the CoIn auditing pipeline: ### 1. Tokens2Block Matching Head (Model A) - **Purpose**: Verifies that sampled token IDs match their corresponding reasoning blocks - **Architecture**: `sentence-transformers/all-MiniLM-L6-v2` base encoder + cosine similarity matching head - **Input**: Token ID embeddings (mean-pooled) + reasoning block text embedding - **Output**: Match probability (0-1) ### 2. Block2Answer Matching Head (Model B) - **Purpose**: Verifies that each reasoning block is semantically relevant to the final answer - **Architecture**: `sentence-transformers/all-…399efd3
-
Upload folder using huggingface_hub
Verified signature91aec72
-
initial commit
Verified signature13c493c