关于chinese-alpaca-2-7b-64k模型在inference_hf.py推理部署中使用vllm报错的问题

[hoohooer]

提交前必须检查以下项目

• [X] 请确保使用的是仓库最新代码（git pull），一些问题已被解决和修复。
• [X] 我已阅读项目文档和FAQ章节并且已在Issue中对问题进行了搜索，没有找到相似问题和解决方案。
• [x] 第三方插件问题：例如llama.cpp、LangChain、text-generation-webui等，同时建议到对应的项目中查找解决方案。

问题类型

模型量化和部署

基础模型

Others

操作系统

Linux

详细描述问题

# 这是运行命令

python scripts/inference/inference_hf.py --base_model model/chinese-alpaca-2-7b-64k --with_prompt --interactive --use_vllm

依赖情况（代码类问题务必提供）

# 请在此处粘贴依赖情况（请粘贴在本代码块里）

bitsandbytes 0.41.1 peft 0.3.0 sentencepiece 0.1.99 torch 2.1.2 torchvision 0.16.2 transformers 4.36.2

运行日志或截图

# 请在此处粘贴运行日志（请粘贴在本代码块里）

USE_XFORMERS_ATTENTION: True STORE_KV_BEFORE_ROPE: False Traceback (most recent call last): File "/hy-tmp/Aplaca2/Chinese-LLaMA-Alpaca-2-main/scripts/inference/inference_hf.py", line 129, in model = LLM(model=args.base_model, File "/usr/local/miniconda3/lib/python3.10/site-packages/vllm/entrypoints/llm.py", line 105, in init self.llm_engine = LLMEngine.from_engine_args(engine_args) File "/usr/local/miniconda3/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 304, in from_engine_args engine_configs = engine_args.create_engine_configs() File "/usr/local/miniconda3/lib/python3.10/site-packages/vllm/engine/arg_utils.py", line 218, in create_engine_configs model_config = ModelConfig(self.model, self.tokenizer, File "/usr/local/miniconda3/lib/python3.10/site-packages/vllm/config.py", line 101, in init self.hf_config = get_config(self.model, trust_remote_code, revision) File "/usr/local/miniconda3/lib/python3.10/site-packages/vllm/transformers_utils/config.py", line 35, in get_config raise e File "/usr/local/miniconda3/lib/python3.10/site-packages/vllm/transformers_utils/config.py", line 23, in get_config config = AutoConfig.from_pretrained( File "/usr/local/miniconda3/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 1099, in from_pretrained return config_class.from_dict(config_dict, unused_kwargs) File "/usr/local/miniconda3/lib/python3.10/site-packages/transformers/configuration_utils.py", line 774, in from_dict config = cls(config_dict) File "/usr/local/miniconda3/lib/python3.10/site-packages/transformers/models/llama/configuration_llama.py", line 160, in init self._rope_scaling_validation() File "/usr/local/miniconda3/lib/python3.10/site-packages/transformers/models/llama/configuration_llama.py", line 180, in _rope_scaling_validation raise ValueError( ValueError: rope_scaling must be a dictionary with with two fields, type and factor, got {'factor': 16.0, 'finetuned': True, 'original_max_position_embeddings': 4096, 'type': 'yarn'}

[hoohooer]

依赖情况已更新，还是报相同的错误。 bitsandbytes 0.42.0 peft 0.7.1 sentencepiece 0.1.99 torch 2.1.2 torchvision 0.16.2 transformers 4.36.2

[iMountTai]

chinese-alpaca-2-7b-64k需要通过文件夹下的modeling_llama_yarn.py加载，这是自编写的模型文件，vllm可能不支持这个操作。

[hoohooer]

chinese-alpaca-2-7b-64k需要通过文件夹下的modeling_llama_yarn.py加载，这是自编写的模型文件，vllm可能不支持这个操作。

请问是哪个文件夹？我在项目文件中没找到modeling_llama_yarn.py。非常感谢！

[iMountTai]

与模型权重在同一个目录下，不在项目文件中

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your consideration.

[github-actions[bot]]

Closing the issue, since no updates observed. Feel free to re-open if you need any further assistance.