GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
antontuzovAI
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
antontuzovAI
Model Tree
openbmb/MiniCPM5-2B
Input Modalities
Output Modalities
Supported Functionality
[{"name": "tool", "arguments": {...}}] directly.You need the base model and peft to load this adapter.
python
import torchimport jsonfrom transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfigfrom peft import PeftModel model_id = "openbmb/MiniCPM5-2B"adapter_id = "antontuzovAI/MiniCPM5-2B-xLAM-Agent-LoRA" # Replace with your actual repo ID bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16,) tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)tokenizer.pad_token = tokenizer.eos_token base_model = AutoModelForCausalLM.from_pretrained( model_id, quantization_config=bnb_config, device_map="auto", trust_remote_code=True) # Load the Agent LoRAmodel = PeftModel.from_pretrained(base_model, adapter_id)model.eval() # Define Toolstools = [ { "name": "get_weather", "description": "Get current weather.", "parameters": {"city": {"type": "string", "required": True}} }] prompt = f"""You are a strict tool-calling agent. Output ONLY JSON.Tools: {json.dumps(tools)}User: What is the weather in Tokyo?Assistant:""" inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=64, do_sample=False)print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))# Expected Output: [{"name": "get_weather", "arguments": {"city": "Tokyo"}}]import torchimport jsonfrom transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfigfrom peft import PeftModel model_id = "openbmb/MiniCPM5-2B"adapter_id = "antontuzovAI/MiniCPM5-2B-xLAM-Agent-LoRA" # Replace with your actual repo ID bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16,) tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)tokenizer.pad_token = tokenizer.eos_token base_model = AutoModelForCausalLM.from_pretrained( model_id, quantization_config=bnb_config, device_map="auto", trust_remote_code=True) # Load the Agent LoRAmodel = PeftModel.from_pretrained(base_model, adapter_id)model.eval() # Define Toolstools = [ { "name": "get_weather", "description": "Get current weather.", "parameters": {"city": {"type": "string", "required": True}} }] prompt = f"""You are a strict tool-calling agent. Output ONLY JSON.Tools: {json.dumps(tools)}User: What is the weather in Tokyo?Assistant:""" inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=64, do_sample=False)print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))# Expected Output: [{"name": "get_weather", "arguments": {"city": "Tokyo"}}]