GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
beyoru
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
beyoru
Model Tree
beyoru/Kiwen1.1-27B
Input Modalities
Output Modalities
Supported Functionality
RL in internal workflow by RLVR
| Rank | Model | Pass Rate | Partial Rate |
|---|---|---|---|
| 1 | Kiwen1.2 | 81.2% | 89.62% |
| 2 | gemini-3.7-flash | 81.0% | 89.8% |
| 3 | gemini-3.6-flash | 80.0% | 88.9% |
| 4 | Kiwen1.1 | 78.1% | 87.85% |
the benchmark includes 100 internal tasks for agent workflow
python
from transformers import AutoModelForCausalLM, AutoTokenizerm = "beyoru/Kiwen1.1-27B"tok = AutoTokenizer.from_pretrained(m)model = AutoModelForCausalLM.from_pretrained(m, dtype="auto", device_map="auto")msgs = [{"role": "user", "content": "Natalia sold clips to 48 friends in April, ""and half as many in May. How many total?"}]ids = tok.apply_chat_template(msgs, add_generation_prompt=True,enable_thinking=True, return_tensors="pt").to(model.device)print(tok.decode(model.generate(ids, max_new_tokens=4096)[0][ids.shape[-1]:]))
Set enable_thinking=False for extraction, classification and formatting tasks.
The model was trained with both modes and respects the flag.
Serving with SGLang:
bash
python -m sglang.launch_server --model-path beyoru/Kiwen1.2-27B \--context-length 262144
bibtex
@misc{kiwen27bk3,title = {Kiwen1.2-27B},author = {beyoru},year = {2026},url = {https://huggingface.co/beyoru/Kiwen1.2-27B}}
Built on:
Kiwen1.2-27B is released under the Apache-2.0 license.