Text Classification
Transformers
Safetensors
Korean
English
modernbert
llm-guard
guardrails
code-detection
korean
Instructions to use ThakiCloud/Thaki-BanCode-KoEn-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ThakiCloud/Thaki-BanCode-KoEn-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ThakiCloud/Thaki-BanCode-KoEn-v2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("ThakiCloud/Thaki-BanCode-KoEn-v2") model = AutoModelForSequenceClassification.from_pretrained("ThakiCloud/Thaki-BanCode-KoEn-v2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download bancode.py from ThakiCloud/Thaki-BanCode-KoEn-v2: direct link, hf CLI and curl.
- Browser
- Download file 2.54 kB
-
https://huggingface.co/ThakiCloud/Thaki-BanCode-KoEn-v2/resolve/main/bancode.py
- Command line
-
hf download hf://ThakiCloud/Thaki-BanCode-KoEn-v2/bancode.py
-
curl -L -o bancode.py https://huggingface.co/ThakiCloud/Thaki-BanCode-KoEn-v2/resolve/main/bancode.py
2.54 kB
| # SPDX-License-Identifier: MIT | |
| # Copyright (c) 2026 ThakiCloud | |
| """BanCode v2 inference wrapper (CPU or GPU). | |
| The tokenizer is NOT part of this repository. It is loaded from jhu-clsp/mmBERT-small at the exact | |
| revision pinned in bancode_v2_profile.json and keeps its own terms (see NOTICE.md). | |
| python bancode.py <model_dir_or_repo_id> "text one" "text two" | |
| """ | |
| import json | |
| import os | |
| import sys | |
| import torch | |
| from transformers import AutoModelForSequenceClassification, AutoTokenizer | |
| PROFILE = "bancode_v2_profile.json" | |
| def _profile_path(model, revision=None): | |
| if os.path.isdir(model): | |
| return os.path.join(model, PROFILE) | |
| from huggingface_hub import hf_hub_download | |
| return hf_hub_download(model, PROFILE, revision=revision) | |
| class BanCodeV2: | |
| def __init__(self, model=".", revision=None, device="cpu"): | |
| with open(_profile_path(model, revision), encoding="utf-8") as f: | |
| self.profile = json.load(f) | |
| t = self.profile["tokenizer"] | |
| self.tokenizer = AutoTokenizer.from_pretrained(t["repo"], revision=t["revision"]) | |
| self.model = AutoModelForSequenceClassification.from_pretrained(model, revision=revision).eval().to(device) | |
| self.device = device | |
| self.code_idx = int(self.model.config.label2id[self.profile["code_label"]]) | |
| def logits(self, texts): | |
| enc = self.tokenizer(list(texts), truncation=True, max_length=self.profile["max_length"], | |
| padding=True, return_tensors="pt").to(self.device) | |
| with torch.inference_mode(): | |
| return self.model(**enc).logits.float() | |
| def p_code(self, texts): | |
| return torch.softmax(self.logits(texts), -1)[:, self.code_idx].tolist() | |
| def scan(self, prompt): | |
| """LLM Guard scanner contract: (sanitized_prompt, is_valid, risk_score). Raw text, no preprocessing.""" | |
| if prompt.strip() == "": | |
| return prompt, True, -1.0 | |
| s, t = self.p_code([prompt])[0], self.profile["threshold"] | |
| risk = round((s - t) / (1 - t), 1) if s > t else round((s - t) / t, 1) | |
| return prompt, not (s > t), min(max(risk, -1.0), 1.0) | |
| if __name__ == "__main__": | |
| m = BanCodeV2(sys.argv[1] if len(sys.argv) > 1 else ".") | |
| for text in sys.argv[2:] or ["Please summarise the meeting notes from Thursday.", | |
| "Run this:\n```bash\npip install requests\n```"]: | |
| _, ok, risk = m.scan(text) | |
| print(json.dumps({"code_detected": not ok, "risk_score": risk, "text": text[:40]}, ensure_ascii=False)) | |