Description
是否和2.0版本一致，如下：
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
from swift.llm import (
get_model_tokenizer, get_template, inference, ModelType,
get_default_template_type, inference_stream
)
from swift.utils import seed_everything
import torch
model_type = ModelType.minicpm_v_v2_6_chat
model_id_or_path = None
template_type = get_default_template_type(model_type)
print(f'template_type: {template_type}')
model, tokenizer = get_model_tokenizer(model_type, torch.bfloat16, model_id_or_path=model_id_or_path,
model_kwargs={'device_map': 'auto'})
model.generation_config.max_new_tokens = 256
template = get_template(template_type, tokenizer)
seed_everything(42)
query = '
流式（streaming）
query = '描述这张图片'
images = ['http://modelscope-open.oss-cn-hangzhou.aliyuncs.com/images/cat.png']
gen = inference_stream(model, template, query, images=images)
print_idx = 0
print(f'query: {query}\nresponse: ', end='')
for response, history in gen:
delta = response[print_idx:]
print(delta, end='', flush=True)
print_idx = len(response)
print()
"""
query: