README.md

---
language: 
  - zh
  - en
  - de
  - fr
license: mit
pipeline_tag: feature-extraction
library_name: transformers
tags:
  - embeddings
  - lora
  - sociology
  - retrieval
  - feature-extraction
  - sentence-transformers
---

# THETA: Textual Hybrid Embedding–based Topic Analysis

## Model Description

THETA is a domain-specific embedding model fine-tuned using LoRA on top of Qwen3-Embedding models (0.6B and 4B). It is designed to generate dense vector representations for texts in the sociology and social science domain.

The model is suitable for tasks such as semantic search, similarity computation, clustering, and retrieval-augmented generation (RAG).

**Base Models:**
- [Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B)
- [Qwen3-Embedding-4B](https://huggingface.co/Qwen/Qwen3-Embedding-4B)

**Fine-tuning Methods:**
- **Unsupervised:** SimCSE (contrastive learning)
- **Supervised:** Label-guided contrastive learning with LoRA

## Intended Use

This model is intended for text embedding generation, semantic similarity computation, document retrieval, and downstream NLP tasks requiring dense representations.

It is **not** designed for text generation or decision-making in high-risk scenarios.

## Model Architecture

| Component | Detail |
|---|---|
| Base model | Qwen3-Embedding (0.6B / 4B) |
| Fine-tuning | LoRA (Low-Rank Adaptation) |
| Output dimension | 896 (0.6B) / 2560 (4B) |
| Framework | Transformers (PyTorch) |

## Repository Structure

```
CodeSoulco/THETA/
├── 0.6B/
│   ├── supervised/
│   └── unsupervised/
├── 4B/
│   ├── supervised/
│   └── unsupervised/
└── logs/
```

Pre-computed embeddings are available in a separate dataset repo: [CodeSoulco/THETA-embeddings](https://huggingface.co/datasets/CodeSoulco/THETA-embeddings)

## Training Details

- **Fine-tuning method:** LoRA
- **Training domain:** Sociology and social science texts
- **Datasets:** germanCoal, FCPB, socialTwitter, hatespeech, mental_health
- **Objective:** Improve domain-specific semantic representation
- **Hardware:** Dual NVIDIA GPU

## How to Use

```python
from transformers import AutoTokenizer, AutoModel
from peft import PeftModel
import torch

# Load base model
base_model = AutoModel.from_pretrained("Qwen/Qwen3-Embedding-0.6B", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-Embedding-0.6B", trust_remote_code=True)

# Load LoRA adapter
model = PeftModel.from_pretrained(
    base_model,
    "CodeSoulco/THETA",
    subfolder="0.6B/unsupervised/germanCoal"
)

# Generate embeddings
text = "Social structure and individual behavior"
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)

with torch.no_grad():
    outputs = model(**inputs)

embeddings = outputs.last_hidden_state[:, 0, :]  # CLS token
```

## Limitations

- Fine-tuned for sociology/social science domain; may not generalize well to unrelated topics.
- Performance depends on input text length and quality.
- Does not generate text and should not be used for generative tasks.

## License

This model is released under the **MIT License**.

## Citation

```bibtex
@misc{theta2026,
  title={THETA: Textual Hybrid Embedding--based Topic Analysis},
  author={CodeSoul},
  year={2026},
  publisher={Hugging Face},
  url={https://huggingface.co/CodeSoulco/THETA}
}
```