THETA

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

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