| ``` | |
| from transformers import AutoTokenizer, AutoModelForCausalLM, AutoConfig | |
| import torch | |
| model_path = 'efficient-llm/vicuna-13b-v1.3-wanda' | |
| config = AutoConfig.from_pretrained(model_path, revision='0.5_2to4', trust_remote_code=True) | |
| enc = AutoTokenizer.from_pretrained('lmsys/vicuna-13b-v1.3', trust_remote_code=True) | |
| kwargs = {"torch_dtype": torch.float16, "low_cpu_mem_usage": True} | |
| model = AutoModelForCausalLM.from_pretrained( | |
| model_path, config=config, trust_remote_code=True, device_map='auto', revision='0.5_2to4', **kwargs) | |
| model.eval() | |
| input_ids = enc('How are you today?', return_tensors='pt').input_ids.to('cuda') | |
| outputs = model.generate(input_ids=input_ids, max_length=128) | |
| print(enc.decode(outputs[0])) | |
| ``` | |