GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
nphearum
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
nphearum
Model Tree
Input Modalities
Output Modalities
Supported Functionality
This repository contains the standard Hugging Face model export:
| File | Purpose |
|---|---|
model.safetensors | model weights |
config.json | model architecture/config |
tokenizer.json | tokenizer |
tokenizer_config.json | tokenizer metadata and special tokens |
processor_config.json | multimodal processor config |
chat_template.jinja | chat formatting template |
generation_config.json | generation defaults |
python
import torchfrom transformers import AutoProcessor, AutoModelForCausalLMrepo_id = "nphearum/PsarAI-2B"processor = AutoProcessor.from_pretrained(repo_id, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained(repo_id,torch_dtype=torch.bfloat16,device_map="auto",trust_remote_code=True,)messages = [{"role": "user", "content": "Who created you?"}]prompt = processor.tokenizer.apply_chat_template(messages,tokenize=False,add_generation_prompt=True,enable_thinking=False,)inputs = processor.tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs,max_new_tokens=256,temperature=0.7,top_p=0.9,)print(processor.tokenizer.decode(outputs[0], skip_special_tokens=False))
The template uses Gemma-style tokens:
<|turn>system<|turn>user<|turn>model<turn|><|channel>thought<|tool_call><|tool_response>For normal chatbot use, disable visible thinking when your runtime supports template kwargs:
python
enable_thinking=False
python
temperature = 0.7top_p = 0.9max_new_tokens = 512
Use lower temperature, such as 0.2, for factual or deterministic answers.
The config includes image, audio, and video processor metadata. Runtime support depends on the installed transformers version and model implementation availability.
For GGUF/llama.cpp usage, use the sibling GGUF export repo instead:
text
nphearum/PsarAI-2B-GGUF
Base model metadata in this export is:
text
nphearum/psarai-2b
Keep this metadata for traceability when publishing derived formats.