4bit版本使用modelscope拉取，inference时一直显示获取模型版本失败

bug:
```shell
Traceback (most recent call last):
File "/DATA/DATA1/renxiaoyu/202403_mllm/code/internlm-xcomposer_inference.py", line 33, in
model = InternLMXComposer2QForCausalLM.from_quantized(model_dir, trust_remote_code=True, device="cuda:0").eval()
File "/home/huiyu/.conda/envs/llava/lib/python3.10/site-packages/auto_gptq/modeling/_base.py", line 1028, in from_quantized
model = AutoModelForCausalLM.from_config(
File "/home/huiyu/.conda/envs/llava/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 438, in from_config
return model_class._from_config(config, **kwargs)
File "/home/huiyu/.conda/envs/llava/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1334, in _from_config
model = cls(config, **kwargs)
File "/home/huiyu/.cache/huggingface/modules/transformers_modules/internlm-xcomposer2-vl-7b-4bit/modeling_internlm_xcomposer2.py", line 67, in __init__
self.vit = build_vision_tower()
File "/home/huiyu/.cache/huggingface/modules/transformers_modules/internlm-xcomposer2-vl-7b-4bit/build_mlp.py", line 11, in build_vision_tower
return CLIPVisionTower(vision_tower)
File "/home/huiyu/.cache/huggingface/modules/transformers_modules/internlm-xcomposer2-vl-7b-4bit/build_mlp.py", line 58, in __init__
self.load_model()
File "/home/huiyu/.cache/huggingface/modules/transformers_modules/internlm-xcomposer2-vl-7b-4bit/build_mlp.py", line 62, in load_model
self.vision_tower = CLIPVisionModel.from_pretrained(
File "/home/huiyu/.conda/envs/llava/lib/python3.10/site-packages/modelscope/utils/hf_util.py", line 68, in from_pretrained
model_dir = snapshot_download(
File "/home/huiyu/.conda/envs/llava/lib/python3.10/site-packages/modelscope/hub/snapshot_download.py", line 117, in snapshot_download
revision_detail = _api.get_valid_revision_detail(
File "/home/huiyu/.conda/envs/llava/lib/python3.10/site-packages/modelscope/hub/api.py", line 494, in get_valid_revision_detail
all_branches_detail, all_tags_detail = self.get_model_branches_and_tags_details(
File "/home/huiyu/.conda/envs/llava/lib/python3.10/site-packages/modelscope/hub/api.py", line 574, in get_model_branches_and_tags_details
handle_http_response(r, logger, cookies, model_id)
File "/home/huiyu/.conda/envs/llava/lib/python3.10/site-packages/modelscope/hub/errors.py", line 98, in handle_http_response
raise HTTPError('Response details: %s, Request id: %s' %
requests.exceptions.HTTPError: Response details: {'Code': 10010205001, 'Message': '获取模型版本失败，信息：record not found', 'RequestId': 'e8ad3691-6698-4bbc-aa14-823212d6dcfe', 'Success': False}, Request id: 78d60112e7f54592839c6c94e8f560c0
```