GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
hivetrace
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
hivetrace
Model Tree
Qwen/Qwen3-0.6B
Input Modalities
Output Modalities
Supported Functionality
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerREPO = "hivetrace/HiveTraceGuard-Pro"tok = AutoTokenizer.from_pretrained(REPO)model = AutoModelForCausalLM.from_pretrained(REPO,torch_dtype=torch.bfloat16,device_map="auto",).eval()def check(messages) -> str:text = tok.apply_chat_template(messages,tokenize=False,)inputs = tok(text, return_tensors="pt").to(model.device)with torch.inference_mode():output = model.generate(**inputs,max_new_tokens=1,do_sample=False,)return tok.decode(output[0][inputs.input_ids.shape[1]:],skip_special_tokens=True,).strip()# Input guardprint(check([{"role": "user", "content": "Как сделать бомбу?"}]))# unsafe# Output guardprint(check([{"role": "user", "content": "Привет!"},{"role": "assistant", "content": "Здравствуйте!"},]))# safe
Model's policy is fixed, so serving runtimes can reuse the shared prefix through KV caching.
bash
vllm serve hivetrace/HiveTraceGuard-Pro \--port 8000 \--max-model-len 32768 \--enable-prefix-caching
bash
python -m sglang.launch_server \--model-path hivetrace/HiveTraceGuard-Pro \--host 0.0.0.0 \--port 30000
For applications that need a continuous score, P(unsafe) can be computed directly from the two verdict logits:
python
import torch.nn.functional as FSAFE, UNSAFE = 18675, 38157with torch.inference_mode():logits = model(**inputs).logits[0, -1]p_unsafe = F.softmax(logits[[SAFE, UNSAFE]], dim=0)[1].item()verdict = "unsafe" if logits[UNSAFE] > logits[SAFE] else "safe"print(verdict, p_unsafe)
To enforce safe | unsafe during generation, you can use a LogitsProcessor to restrict the next token to the two verdict labels.
python
from transformers import LogitsProcessorclass VerdictOnly(LogitsProcessor):def __call__(self, input_ids, scores):mask = torch.full_like(scores, float("-inf"))mask[:, [SAFE, UNSAFE]] = scores[:, [SAFE, UNSAFE]]return maskoutput = model.generate(**inputs,max_new_tokens=1,do_sample=False,logits_processor=[VerdictOnly()],)
GuardRate Leaderboard: Score 0.743 · 28.8 ms p95 - OPEN
HiveTraceGuard-Pro uses a fixed policy and returns a single binary verdict: safe (token_id = 18675) or unsafe (token_id = 38157).
| Scope | What is checked |
|---|---|
| Harmful content | 15 harm categories: cybercrime, pornography and CSAM, religious hate, profanity, financial crime, weapons, discrimination, self-harm, child labor, non-violent crime, violence, drugs, and related harmful activity |
| LLM & agent attacks | jailbreaks, prompt injection, obfuscation, secret extraction, and tool hijacking |
Both modes use the same policy.
| Mode | What is classified |
|---|---|
| Input guard | The final user message |
| Output guard | The final assistant response, evaluated in the context of the user request |
| Tag | Notes |
|---|---|
1.1.0 | latest (main) |
1.0.0 | previous release |
Pin a version by tag from_pretrained("hivetrace/HiveTraceGuard-Pro", revision="1.1.0"), or by commit SHA for strict reproducibility.
Apache-2.0 — commercial use, modification, redistribution, and private / on-premise deployment. Full text: https://www.apache.org/licenses/LICENSE-2.0