ValueError: too many values to unpack (expected 2)怎么解决？

#70

by jackleef - opened Jul 30

Jul 30

ValueError Traceback (most recent call last)
Cell In[9], line 25
23 gen_kwargs = {"max_length": 2500, "do_sample": True, "top_k": 1}
24 with torch.no_grad():
---> 25 outputs = model.generate(**inputs, **gen_kwargs)
26 outputs = outputs[:, inputs['input_ids'].shape[1]:]
27 print(tokenizer.decode(outputs[0], skip_special_tokens=True))

ValueError: too many values to unpack (expected 2)

ps：用的是官方demo

jackleef

Jul 30

加载模型

device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_dir,trust_remote_code=True)

query = "你好"

inputs = tokenizer.apply_chat_template([{"role": "user", "content": query}],
add_generation_prompt=True,
tokenize=True,
return_tensors="pt",
return_dict=True
)

inputs = inputs.to(device)
model = AutoModelForCausalLM.from_pretrained(
model_dir,
torch_dtype=torch.bfloat16,
low_cpu_mem_usage=True,
trust_remote_code=True
).to(device).eval()

gen_kwargs = {"max_length": 2500, "do_sample": True, "top_k": 1}
with torch.no_grad():
outputs = model.generate(**inputs, **gen_kwargs)
outputs = outputs[:, inputs['input_ids'].shape[1]:]
print(tokenizer.decode(outputs[0], skip_special_tokens=True))