GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
giangkh19
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
giangkh19
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj0.0978python
import torchfrom unsloth import FastLanguageModel # 1. Nạp Base Model dạng 4-bit (chỉ tốn ~2.5GB VRAM)model, tokenizer = FastLanguageModel.from_pretrained( model_name="Qwen/Qwen3.5-4B", max_seq_length=2048, load_in_4bit=True,) # 2. Gắn LoRA Adapter từ Hugging Facemodel = FastLanguageModel.get_peft_model(model)model.load_adapter("giangkh19/Qwen3.5-4B-Financial-SQL-LoRA")FastLanguageModel.for_inference(model) # 3. Suy luậnprompt = "<|im_start|>user\nTổng tài sản năm 2023 của Vinamilk (VNM) là bao nhiêu?<|im_end|>\n<|im_start|>assistant\n"inputs = tokenizer(prompt, return_tensors="pt").to("cuda")outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.01)print(tokenizer.decode(outputs[0], skip_special_tokens=False))