shudct

> # 加载模型 > model = AutoModelForCausalLM.from_pretrained( > args.model_name_or_path, > device_map="auto", > load_in_4bit=True, > torch_dtype=torch.float16, > trust_remote_code=True, > quantization_config=BitsAndBytesConfig( > load_in_4bit=True, > bnb_4bit_compute_dtype=torch.float16, > bnb_4bit_use_double_quant=True, > bnb_4bit_quant_type="nf4", > llm_int8_threshold=6.0, >...

@Robert-JunWang Thank for your explanation. Caffe seems not support float16 for training and inference. Can you give me some advice for store the weights? THX!

@simon-rob i notice when testing, img = img * 0.017. can you explain why?

@simon-rob I have tested without img = img * 0.017, the result is completely wrong. Usually, the code to normalize the input is by 1/255. I'm confused to the exact...

你好想请教一个问题，如果我想评测自己的数据集（微调之后，但是微调数据集就是问答对，并没有选择ABCD，这个需要怎么评估呢