GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
cs-552-2026-ChatMODS
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
cs-552-2026-ChatMODS
Model Tree
Qwen/Qwen3-1.7B
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen3-1.7Bsafetensorsgeneration_config.json is includedchat_template.jinja is includedThe tokenizer chat template injects a safety-classification system prompt and requires the model to answer with exactly one boxed label:
\boxed{harmful}\boxed{safe}The generation prompt includes the empty Qwen3 non-thinking stub:
text
<think></think>The checkpoint was validated locally with:
python
from transformers import AutoTokenizer tok = AutoTokenizer.from_pretrained("./safety_model_checkpoint")print(tok.apply_chat_template( [{"role": "user", "content": "What is 2+2?"}], tokenize=False, add_generation_prompt=True,))