GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
DDoo1204
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
DDoo1204
Model Tree
unsloth/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
unsloth/Qwen3.5-4Br=16, lora_alpha=32, all 12 linear modules targeted)supervised_fraction ~41.5%)python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelimport torchbase_model_id = "unsloth/Qwen3.5-4B"adapter_id = "DDoo1204/Day21-Track3-2A202601564-PhamQuyDo-LoRA"tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained(base_model_id,torch_dtype=torch.float16,device_map="auto",trust_remote_code=True)model = PeftModel.from_pretrained(model, adapter_id)model.eval()prompt = "Khách hàng: Shop ơi, mình đặt áo khoác gió mã đơn VN613097. Bị rách tay áo. Đổi giúp mình với."messages = [{"role": "user", "content": prompt}]inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to("cuda")outputs = model.generate(inputs, max_new_tokens=128)print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))