from sentence_transformers import SentenceTransformer

m = SentenceTransformer("anonymousresearch123/deka-qwen3-emb-0.6b-weight-lay")
q = m.encode(["ลูกจ้างถูกเลิกจ้างโดยไม่บอกกล่าวล่วงหน้า"], prompt_name="query")
d = m.encode(["<คำพิพากษาฎีกา ...>"])
print(m.similarity(q, d))

Plain transformers:

python

import torch, torch.nn.functional as F
from transformers import AutoModel, AutoTokenizer

tok = AutoTokenizer.from_pretrained("anonymousresearch123/deka-qwen3-emb-0.6b-weight-lay", padding_side="left")
net = AutoModel.from_pretrained("anonymousresearch123/deka-qwen3-emb-0.6b-weight-lay", torch_dtype=torch.bfloat16).eval()

INSTRUCT = "Given a legal case search query, retrieve relevant prior Supreme Court cases"
texts = [f"Instruct: {INSTRUCT}\nQuery: ลูกจ้างถูกเลิกจ้าง..."]   # query side only
enc = tok(texts, padding=True, truncation=True, max_length=1300, return_tensors="pt")
with torch.no_grad():
    h = net(**enc).last_hidden_state
emb = F.normalize(h[:, -1].float(), p=2, dim=-1)

Left padding is required — pooling takes the last position.

Training data

anonymousresearch123/deka-retrieval — splits train / eval / test. training_history.json in this repo holds the full per-epoch log and config.