NMIXX-QWEN

This repository contains a gte-Qwen2-1.5B-instruct-based SentenceTransformer model fine-tuned with a triplet-loss setup on the nmixx-fin/NMIXX_train dataset. It produces high-quality sentence embeddings for Korean financial text, optimized for semantic similarity tasks in the finance domain.

---

How to Use

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

def last_token_pool(last_hidden_states, attention_mask):
    """
    Last token pooling for decoder-based models like GTE-Qwen
    """
    left_padding = (attention_mask[:, -1].sum() == attention_mask.shape[0])
    if left_padding:
        return last_hidden_states[:, -1]
    else:
        sequence_lengths = attention_mask.sum(dim=1) - 1
        batch_size = last_hidden_states.shape[0]
        return last_hidden_states[torch.arange(batch_size, device=last_hidden_states.device), sequence_lengths]

# 1. Load tokenizer & model from Hugging Face Hub
repo_name = "nmixx-fin/nmixx-qwen"
tokenizer = AutoTokenizer.from_pretrained(repo_name)
model = AutoModel.from_pretrained(repo_name)

# 2. Move to GPU if available
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
model.eval()

# 3. Prepare input sentences
sentences = [
    "이 모델은 한국 금융 도메인에 특화된 임베딩을 제공합니다.",
    "NMIXX 데이터셋으로 fine-tuning된 sentence transformer입니다."
]

# 4. Tokenize
encoded_input = tokenizer(
    sentences,
    padding=True,
    truncation=True,
    max_length=512,
    return_tensors="pt"
)
input_ids = encoded_input["input_ids"].to(device)
attention_mask = encoded_input["attention_mask"].to(device)

# 5. Forward pass (token embeddings)
with torch.no_grad():
    model_output = model(input_ids=input_ids, attention_mask=attention_mask)

# 6. Last Token Pooling (GTE-Qwen uses last token)
sentence_embeddings = last_token_pool(model_output.last_hidden_state, attention_mask)

# 7. L2 Normalization
sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)

print("Sentence embeddings shape:", sentence_embeddings.shape)
print(sentence_embeddings.cpu())