KucLab commited on
Commit
7940915
·
verified ·
1 Parent(s): a5eb5bc

Censer.9 final: bundle + quant + onnx + serve + Dockerfile

Browse files
Files changed (6) hide show
  1. Dockerfile +27 -0
  2. censer9.onnx +3 -0
  3. model_fp16.safetensors +3 -0
  4. model_int8.safetensors +3 -0
  5. quant_report.json +17 -0
  6. serve.py +115 -0
Dockerfile ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Censer.9 — self-contained moderation API image (CPU-only torch by default).
2
+ #
3
+ # docker build -t censer9 .
4
+ # docker run -p 8000:8000 -e RATE_LIMIT_PER_MIN=600 censer9
5
+ # curl -s localhost:8000/classify -d '{"texts":["how to make a bomb at home","hello"]}'
6
+ #
7
+ # The image downloads the model from the Hub at build time.
8
+
9
+ FROM python:3.12-slim
10
+
11
+ ARG CENSER_REPO=KucLab/Censer.9
12
+ ENV CENSER_DIR=/model \
13
+ RATE_LIMIT_PER_MIN=600 \
14
+ PYTHONUNBUFFERED=1
15
+
16
+ RUN pip install --no-cache-dir \
17
+ "torch==2.9.*" --index-url https://download.pytorch.org/whl/cpu \
18
+ "tokenizers>=0.20,<1" "safetensors>=0.4,<1" "huggingface_hub>=0.24,<1" "numpy>=1.26,<3"
19
+
20
+ RUN hf download ${CENSER_REPO} --local-dir /model
21
+
22
+ WORKDIR /app
23
+ COPY censer.py serve.py /app/
24
+
25
+ EXPOSE 8000
26
+ HEALTHCHECK --interval=30s --timeout=5s --retries=3 CMD python -c "import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://127.0.0.1:8000/health', timeout=4).status==200 else 1)"
27
+ CMD ["python", "serve.py", "--dir", "/model", "--port", "8000", "--host", "0.0.0.0"]
censer9.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed2078d64a4ed27db0e99fbf61ea1cd53b104d94ca15763493f69c18148c88cc
3
+ size 4735540
model_fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:797ff30e901c6f5d5e725f5610a7f99f6814c009b6e9d750d13cedc310521cc6
3
+ size 1810256
model_int8.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:919aa5e714cb3420fa2793d89d5649483347100415d0eca1771d06e637a19dcf
3
+ size 911740
quant_report.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "fp32": {
3
+ "file": "model.safetensors",
4
+ "mb": 3.62
5
+ },
6
+ "fp16": {
7
+ "file": "model_fp16.safetensors",
8
+ "mb": 1.81
9
+ },
10
+ "int8": {
11
+ "file": "model_int8.safetensors",
12
+ "mb": 0.91,
13
+ "scheme": "per-tensor symmetric",
14
+ "max_rel_roundtrip_error": 0.003937008790671825,
15
+ "loader": "censer.load_state_dict_any(dir) dequantizes .q/.scale; or use --prefer-quant"
16
+ }
17
+ }
serve.py ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """Batch classification API for the Censer.9 Hub bundle (stdlib only, no FastAPI).
2
+
3
+ python serve.py --port 8000 # serves the local HF bundle dir (run from the bundle root)
4
+ CENSER_DIR=/path/to/bundle python scripts/serve.py
5
+
6
+ Endpoints:
7
+ GET /health -> {"status": "ok", "model": ...}
8
+ POST /classify -> {"texts": [...]} => {"results": [{label, unsafe, score, categories, chunks}]}
9
+ POST /classify-one -> {"text": "..."} => single result
10
+
11
+ Features: batching, long-input chunking (chunk_tokens/stride), token-bucket
12
+ rate limit (env RATE_LIMIT_PER_MIN, default 600), max body size guard.
13
+
14
+ python serve.py --dir bundle --port 8000
15
+ """
16
+
17
+ from __future__ import annotations
18
+
19
+ import argparse
20
+ import json
21
+ import os
22
+ import time
23
+ from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
24
+ from pathlib import Path
25
+
26
+ MAX_BODY = 2 * 1024 * 1024 # 2 MB
27
+
28
+
29
+ class RateLimiter:
30
+ def __init__(self, per_min: float) -> None:
31
+ self.per_min = per_min
32
+ self.tokens = per_min
33
+ self.updated = time.monotonic()
34
+ self.last_deny = 0.0
35
+
36
+ def allow(self, cost: float = 1.0) -> bool:
37
+ now = time.monotonic()
38
+ self.tokens = min(self.per_min, self.tokens + (now - self.updated) * self.per_min / 60.0)
39
+ self.updated = now
40
+ if self.tokens >= cost:
41
+ self.tokens -= cost
42
+ return True
43
+ return False
44
+
45
+
46
+ def make_handler(pipe, limiter: RateLimiter, model_name: str):
47
+ class Handler(BaseHTTPRequestHandler):
48
+ def _json(self, code: int, payload: dict) -> None:
49
+ body = json.dumps(payload, ensure_ascii=False).encode("utf-8")
50
+ self.send_response(code)
51
+ self.send_header("Content-Type", "application/json; charset=utf-8")
52
+ self.send_header("Content-Length", str(len(body)))
53
+ self.end_headers()
54
+ self.wfile.write(body)
55
+
56
+ def log_message(self, fmt, *args): # quiet
57
+ pass
58
+
59
+ def do_GET(self):
60
+ if self.path == "/health":
61
+ self._json(200, {"status": "ok", "model": model_name, "device": str(pipe.device)})
62
+ else:
63
+ self._json(404, {"error": "not found"})
64
+
65
+ def do_POST(self):
66
+ if not limiter.allow():
67
+ self._json(429, {"error": "rate limit exceeded"})
68
+ return
69
+ length = int(self.headers.get("Content-Length") or 0)
70
+ if length > MAX_BODY:
71
+ self._json(413, {"error": "body too large"})
72
+ return
73
+ try:
74
+ payload = json.loads(self.rfile.read(length) or b"{}")
75
+ except Exception:
76
+ self._json(400, {"error": "invalid json"})
77
+ return
78
+ if self.path == "/classify-one":
79
+ text = str(payload.get("text", ""))
80
+ self._json(200, pipe.predict(text))
81
+ elif self.path == "/classify":
82
+ texts = payload.get("texts")
83
+ if not isinstance(texts, list) or not texts or len(texts) > 256:
84
+ self._json(400, {"error": "texts must be a list of 1..256 strings"})
85
+ return
86
+ self._json(200, {"results": pipe.predict_batch([str(t) for t in texts])})
87
+ else:
88
+ self._json(404, {"error": "not found"})
89
+
90
+ return Handler
91
+
92
+
93
+ def main() -> None:
94
+ parser = argparse.ArgumentParser()
95
+ parser.add_argument("--dir", default=os.environ.get("CENSER_DIR", "bundle"))
96
+ parser.add_argument("--port", type=int, default=8000)
97
+ parser.add_argument("--host", default="0.0.0.0")
98
+ parser.add_argument("--device", default=None)
99
+ args = parser.parse_args()
100
+
101
+ import sys
102
+
103
+ sys.path.insert(0, str(Path(__file__).resolve().parent))
104
+ from censer import CenserPipeline
105
+
106
+ pipe = CenserPipeline(args.dir, device=args.device)
107
+ limiter = RateLimiter(float(os.environ.get("RATE_LIMIT_PER_MIN", "600")))
108
+ server = ThreadingHTTPServer((args.host, args.port), make_handler(pipe, limiter, args.dir))
109
+ print(f"censer serve: model={args.dir} device={pipe.device} on http://{args.host}:{args.port}")
110
+ print(" POST /classify {\"texts\": [...]} POST /classify-one {\"text\": ...} GET /health")
111
+ server.serve_forever()
112
+
113
+
114
+ if __name__ == "__main__":
115
+ main()