GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
North-ML1
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
North-ML1
Model Tree
Base
this model
Input Modalities
Text
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Container
python
from transformers import AutoTokenizer, AutoModelForCausalLMimport torchmodel_id = "YOUR_USERNAME/aurora-one-mini-124m"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id)prompt = "What is the capital of France?"messages = [{"role": "user", "content": prompt}]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt")with torch.no_grad():output = model.generate(**inputs,max_new_tokens=80,temperature=0.7,top_p=0.9,do_sample=True,)print(tokenizer.decode(output[0], skip_special_tokens=True))
The companion GGUF files are provided for local runtimes:
aurora_one_mini_deterministic_v2_f16.gguf — highest fidelityaurora_one_mini_deterministic_v2_q4_k_m.gguf — compact CPU-friendly quantizationUse the Q4_K_M file for a fast, low-memory demo. Use the F16 file when preserving maximum quality is more important.
This is an experimental 124M model, not a frontier assistant. It can produce fluent short responses, but it may hallucinate, repeat itself, or answer arithmetic and factual questions incorrectly. For dependable applications, pair it with a calculator, retrieval system, memory layer, and explicit output validation.
The native-ChatML factual smoke test scored 3/20 on a small internal suite. This score is reported to set realistic expectations and should not be interpreted as a general benchmark.
Good fits include:
Avoid using it as the sole source of truth for medical, legal, financial, safety-critical, or factual decision-making.
The model was post-trained using ChatML-style turns:
text
<|im_start|><|user|>Your question<|im_end|><|im_start|><|assistant|>
The included tokenizer metadata contains the required special tokens.
Aurora One Mini was trained as a small-scale independent experiment using PyTorch and a consumer NVIDIA GPU. Contributions, evaluations, and improvements are welcome.
Released for research and experimentation. Add the project’s final license here before redistributing commercially.