Open lionday opened 1 year ago
Is there any specific configuration method? model = AutoModelForCausalLM.from_pretrained(checkpoint,trust_remote_code=True,torch_dtype=torch.float16)
can you give more details on how you're doing generation? fp16 and bf16 are it's faster in my experiments
Is there any specific configuration method? model = AutoModelForCausalLM.from_pretrained(checkpoint,trust_remote_code=True,torch_dtype=torch.float16)