GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
emmaoba
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
emmaoba
Model Tree
microsoft/Phi-4-mini-instruct
Input Modalities
Output Modalities
Supported Functionality
This is a LoRA adapter, not a full model. You download the base model microsoft/Phi-4-mini-instruct and apply this adapter on top. Phi-4-mini is small (3.8B), so it runs on a normal GPU (8 GB+) or even on CPU if you're patient.
bash
pip install torch transformers peft accelerate safetensors
bash
pip install -U "huggingface_hub[cli]"hf auth login
Paste a token from https://huggingface.co/settings/tokens when asked.
run.pypython
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelbase = "microsoft/Phi-4-mini-instruct"adapter = "emmaoba/davanai-2"tokenizer = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base,device_map="auto",torch_dtype="auto",)# Apply the davanai 2 adaptermodel = PeftModel.from_pretrained(model, adapter)model.eval()messages = [{"role": "user", "content": "Hello! Who are you?"}]prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=256, do_sample=True, temperature=0.7)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
bash
python run.py
The first run downloads the base model (once, then cached), then prints davanai 2's reply.