wenda-llm / wenda Goto Github PK

[Document(page_content='药品注册管理办法\n\n（2020年1月22日国家市场监督管理总局令第27号公布 自2020年7月1日起施行）\n\n第一章 总 则', metadata={'source': 'txt_out\药品注册管理办法2020.txt'}), Document(page_content='第一百零九条 国家药品监督管理局依法向社会公布药品注册审批事项清单及法律依据、审批要求和办理时限，向申请人公开药品注册进度，向社会公开批准上市药品的审评结论和依据以及监督检查发现的违法违规行为，接受社会监督。\n\n批准上市药品的说明书应当向社会公开并及时更新。其中，疫苗还应当公开标签内容并及时更新。', metadata={'source': 'txt_out\药品注册管理办法2020.txt'}), Document(page_content='申 请人取得药品注册证书后，为药品上市许可持有人（以下简称持有人）。\n\n第四条 药品注册按照中药、化学药和生物制品等进行分类 注册管理。\n\n中药注册按照中药创新药、中药改良型新药、古代经典名方中药复方制剂、同名同方药等进行分类。\n\n化学药注册按照化学药创新药、化学药改良型新药、仿制药等进行分类。\n\n生物制品注册按照生物制品创新药、生物制品改良型新药、已上市生物制品（含生物类似药）等进行分类。', metadata={'source': 'txt_out\药品注册管理办法2020.txt'})]
127.0.0.1:system:结合以下文段, 用中文回答用户问题。如果无法从中得到答案，忽略文段内容并用中文回答用户问题。

药品注册管理办法
（2020年1月22日国家市场监督管理总局令第27号公布 自2020年7月1日起施行）
第一章 总 则

第一百零九条 国家药品监督管理局依法向社会公布药品注册审批事项清单及法律依据、审批要求和办理时限，向申请人公开药品注册进 度，向社会公开批准上市药品的审评结论和依据以及监督检查发现的违法违规行为，接受社会监督。
批准上市药品的说明书应当向社会公开并及时更新。其中，疫苗还应当公开标签内容并及时更新。

申请人取得药品注册证书后，为药品上市许可持有人（以下简称持有人）。
第四条 药品注册按照中药、化学药和生物制品等进行分类注册管理。
中药注册按照中药创新药、中药改良型新药、古代经典名方中药复方制剂、同名同方药等进行分类。
化学药注册按照化学药创新药、化学药改良型新药、仿制药等进行分类。
生物制品注册按照生物制品创新药、生物制品改良型新药、已上市生物制品（含生物类似药）等进行分类。

user:最新药品注册管理办法发布日期

错误 local variable 'ctx' referenced before assignment local variable 'ctx' referenced before assignment
附件是我导入的语料：

药品注册管理办法2020.txt

pip安装之后，开始迷茫了，不知道接下来做啥啊啊啊。。。。
难道需要去问问gpt咩。。。

webui能够正常使用。

glm模型地址 G:\ChatGLM\WENDAglm\wenda\model\chatglm-6b
rwkv模型地址 ..\RWKV-4-Raven-7B-v7-ChnEng-20230404-ctx2048.pth
rwkv模型参数 cuda fp16i8 *18+
日志记录 True
chunk_size 100
chunk_count 3
Building prefix dict from the default dictionary ...
Loading model from cache C:\Users\69030\AppData\Local\Temp\jieba.cache
Loading model cost 0.516 seconds.
Prefix dict has been built successfully.
Traceback (most recent call last):
File "G:\ChatGLM\WENDAglm\wenda\gen_data.py", line 23, in
data = f.read()
File "G:\ChatGLM\WENDAglm\wenda\WPy64-31090\python-3.10.9.amd64\lib\codecs.py", line 322, in decode
(result, consumed) = self._buffer_decode(data, self.errors, final)
File "G:\ChatGLM\WENDAglm\wenda\WPy64-31090\python-3.10.9.amd64\lib\encodings\utf_16.py", line 61, in _buffer_decode
codecs.utf_16_ex_decode(input, errors, 0, final)
UnicodeDecodeError: 'utf-16-le' codec can't decode bytes in position 88-89: illegal encoding

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "G:\ChatGLM\WENDAglm\wenda\gen_data.py", line 26, in
data = f.read()
File "G:\ChatGLM\WENDAglm\wenda\WPy64-31090\python-3.10.9.amd64\lib\codecs.py", line 322, in decode
(result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd3 in position 3: invalid continuation byte
请按任意键继续. . .

设备配置为：32g 内存，3080 16g 显卡，系统为win11 企业版 22h2
运行包为：懒人版
重启运行后第一遍无任何问题，ctrl+c中断退出后，再次运行，出现如下错误：
D:\pub\wenda\WPy64-31090\python-3.10.9.amd64\lib\site-packages\langchain\chains\conversational_retrieval\base.py:191: UserWarning: ChatVectorDBChain is deprecated - please use from langchain.chains import ConversationalRetrievalChain
warnings.warn(
:914: ImportWarning: _ImportRedirect.find_spec() not found; falling back to find_module()
serving on http://127.0.0.1:17860
Exception in thread Thread-1 (load_model):
Traceback (most recent call last):
File "D:\pub\wenda\WPy64-31090\python-3.10.9.amd64\lib\threading.py", line 1016, in _bootstrap_inner
self.run()
File "D:\pub\wenda\WPy64-31090\python-3.10.9.amd64\lib\threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "D:\pub\wenda\GLM6BAPI.py", line 144, in load_model
model = AutoModel.from_pretrained(glm_path, local_files_only=True, trust_remote_code=True)
File "D:\pub\wenda\WPy64-31090\python-3.10.9.amd64\lib\site-packages\transformers\models\auto\auto_factory.py", line 459, in from_pretrained
return model_class.from_pretrained(
File "D:\pub\wenda\WPy64-31090\python-3.10.9.amd64\lib\site-packages\transformers\modeling_utils.py", line 2362, in from_pretrained
model = cls(config, *model_args, **model_kwargs)
File "C:\Users\adogs/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py", line 927, in init self.lm_head = skip_init(
File "D:\pub\wenda\WPy64-31090\python-3.10.9.amd64\lib\site-packages\torch\nn\utils\init.py", line 52, in skip_init
return module_cls(*args, **kwargs).to_empty(device=final_device)
File "D:\pub\wenda\WPy64-31090\python-3.10.9.amd64\lib\site-packages\torch\nn\modules\module.py", line 1024, in to_empty
return self._apply(lambda t: torch.empty_like(t, device=device))
File "D:\pub\wenda\WPy64-31090\python-3.10.9.amd64\lib\site-packages\torch\nn\modules\module.py", line 820, in _apply
param_applied = fn(param)
File "D:\pub\wenda\WPy64-31090\python-3.10.9.amd64\lib\site-packages\torch\nn\modules\module.py", line 1024, in
return self.apply(lambda t: torch.empty_like(t, device=device))
File "D:\pub\wenda\WPy64-31090\python-3.10.9.amd64\lib\site-packages\torch_refs_init.py", line 4254, in empty_like
return torch.empty_strided(
RuntimeError: [enforce fail at ..\c10\core\impl\alloc_cpu.cpp:72] data. DefaultCPUAllocator: not enough memory: you tried to allocate 1069285376 bytes.

Error: 500 Internal Server Error
Sorry, the requested URL 'http://127.0.0.1:17860/' caused an error:

Internal Server Error
Exception:
AttributeError("'LocalResponse' object has no attribute 'setHeader'")
Traceback:
Traceback (most recent call last):
File "C:\python\lib\site-packages\bottle.py", line 876, in _handle
return route.call(**args)
File "C:\python\lib\site-packages\bottle.py", line 1759, in wrapper
rv = callback(*a, **ka)
File "E:\wenda\wenda.py", line 19, in index
response.setHeader( "Pragma", "no-cache" );
AttributeError: 'LocalResponse' object has no attribute 'setHeader'

给公司做知识库的，建议能够对4个及以上的显卡做兼容，傻瓜式一键开启和配置。

原文件：
%PYTHON% plugins/gen_data_%zsk_type%.py

plugins 路径这里应该加上引号：

%PYTHON% "plugins/gen_data_%zsk_type%.py"

4月9日版那个警告仍然存在，加载过程如下：
glm模型地址 ..\ChatGLM-6B\model
rwkv模型地址 ..\RWKV-4-Raven-7B-v7-ChnEng-20230404-ctx2048.pth
rwkv模型参数 cuda fp16i8 *18+
日志记录 True
知识库类型 x
embeddings模型地址 model\simcse-chinese-roberta-wwm-ext
vectorstore保存地址 xw
chunk_size 200
chunk_count 3
serving on 0.0.0.0:17860 view at http://127.0.0.1:17860/
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
知识库加载完成
C:\Users\ASUS/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1229: DeprecationWarning: invalid escape sequence ?
["?", "？"],
Loading checkpoint shards: 12%|███████▏ | 1/8 [00:00<00:05, 1.33it/s]D:\wenda\WPy64-38100\python-3.8.10.amd64\lib\site-packages\langchain\chains\conversational_retrieval\base.py:191: UserWarning: ChatVectorDBChain is deprecated - please use from langchain.chains import ConversationalRetrievalChain
warnings.warn(
知识库加载完成
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 8/8 [00:05<00:00, 1.58it/s]
模型加载完成

发现给一段超长文本txt，比如全本三国演义，似乎是随机选一段加在我的问题前面？这和我自己加的区别是什么呀~
我把输入文字上限改高了一下，发现4000字就快占满4090的24G显存，请问这正常吗？
感谢大佬的项目，安装很方便。

前端显示的代码没有缩进以及高亮

但是看后端输出的其实是有的：

不是int4的模型，是FP16（无量化）的那个模型。

有没有考虑一下做个视频教程鸭，对我这种小白也友好还能顺带宣传🥰

解压提示“文件已损坏或不是压缩包”，重新下载过很多次都这样，重命名也试过，各种解压软件都试了，求解答呀

我检查了一下，txt_out 下面只有一个文件，但你看截图，出现有三个同名文件，我确实训练过几次，难道在哪里记录了每次的训练结果？

提问后，它开始无限重复回答相同内容，然后我中断了。

Describe the bug
设置 chunk_size 数值没有效果

修改 settings.bat 当中的参数 set chunk_size=200 到更高的数值，实际运行时，观察控制台输出的参考文本(红色)，其截取的长度比修改前没有变化，长度都是约1000字节上下，大概300个中文字左右。
To Reproduce
修改 settings.bat 当中的参数 set chunk_size= 到不同的数值可以复现此问题，例如 400, 800，2000 等。

看描述不错，
希望能加一些如何使用自有资源的描述说明
比如本地一些文档如何喂入的说明。。。
加油噢，关注了

如题

下载懒人包，直接压缩，打开.bat运行就可以吗？

4月5日，仅chatGLM，知识库为sentence-transformers方式 出现错误
报错如下，发生错误，正在重新加载模型

lm模型地址 model\chatglm-6b-int4
embeddings模型地址 model\simcse-chinese-roberta-wwm-ext
vectorstore保存地址 xw
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
D:\zwj\AI\wenda\45sentence-transformers\WPy64-31090\python-3.10.9.amd64\lib\site-packages\langchain\chains\conversational_retrieval\base.py:191: UserWarning: ChatVectorDBChain is deprecated - please use from langchain.chains import ConversationalRetrievalChain
warnings.warn(
:914: ImportWarning: _ImportRedirect.find_spec() not found; falling back to find_module()
serving on http://127.0.0.1:17860
Symbol cudaLaunchKernel not found in C:\Program Files (x86)\NVIDIA Corporation\PhysX\Common\cudart64_65.dll
No compiled kernel found.
Compiling kernels : C:\Users\zwj.cache\huggingface\modules\transformers_modules\local\quantization_kernels_parallel.c
Compiling gcc -O3 -pthread -fopenmp -std=c99 C:\Users\zwj.cache\huggingface\modules\transformers_modules\local\quantization_kernels_parallel.c -shared -o C:\Users\zwj.cache\huggingface\modules\transformers_modules\local\quantization_kernels_parallel.so
'gcc' 不是内部或外部命令，也不是可运行的程序
或批处理文件。
Compile failed, using default cpu kernel code.
Compiling gcc -O3 -fPIC -std=c99 C:\Users\zwj.cache\huggingface\modules\transformers_modules\local\quantization_kernels.c -shared -o C:\Users\zwj.cache\huggingface\modules\transformers_modules\local\quantization_kernels.so
Kernels compiled : C:\Users\zwj.cache\huggingface\modules\transformers_modules\local\quantization_kernels.so
Cannot load cpu kernel, don't use quantized model on cpu.
Using quantization cache
Applying quantization to glm layers
127.0.0.1:你好
错误 Library cublasLt is not initialized Library cublasLt is not initialized
glm模型地址 model\chatglm-6b-int4
embeddings模型地址 model\simcse-chinese-roberta-wwm-ext
vectorstore保存地址 xw
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.

目前有2张卡，请问怎么配置

glm模型地址 model/chatglm-6b rwkv模型地址 model/RWKV-4-Raven-7B-v7-ChnEng-20230404-ctx2048.pth rwkv模型参数 cuda fp16 日志记录 True 知识库类型 x embeddings模型地址 model/simcse-chinese-roberta-wwm-ext vectorstore保存地址 xw LLM模型类型 glm6b chunk_size 400 chunk_count 3 开始读取数据 Traceback (most recent call last): File "/home/wangfh5/anaconda3/envs/wenda/lib/python3.11/site-packages/huggingface_hub/utils/_errors.py", line 259, in hf_raise_for_status response.raise_for_status() File "/home/wangfh5/anaconda3/envs/wenda/lib/python3.11/site-packages/requests/models.py", line 1021, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/api/models/model/simcse-chinese-roberta-wwm-ext The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/home/wangfh5/AIGC_projects/wenda/plugins/gen_data_x.py", line 39, in embeddings = HuggingFaceEmbeddings(model_name=settings.embeddings_path) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/wangfh5/anaconda3/envs/wenda/lib/python3.11/site-packages/langchain/embeddings/huggingface.py", line 39, in init self.client = sentence_transformers.SentenceTransformer(self.model_name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/wangfh5/anaconda3/envs/wenda/lib/python3.11/site-packages/sentence_transformers/SentenceTransformer.py", line 87, in init snapshot_download(model_name_or_path, File "/home/wangfh5/anaconda3/envs/wenda/lib/python3.11/site-packages/sentence_transformers/util.py", line 442, in snapshot_download model_info = _api.model_info(repo_id=repo_id, revision=revision, token=token) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/wangfh5/anaconda3/envs/wenda/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 120, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/home/wangfh5/anaconda3/envs/wenda/lib/python3.11/site-packages/huggingface_hub/hf_api.py", line 1624, in model_info hf_raise_for_status(r) File "/home/wangfh5/anaconda3/envs/wenda/lib/python3.11/site-packages/huggingface_hub/utils/_errors.py", line 291, in hf_raise_for_status raise RepositoryNotFoundError(message, response) from e huggingface_hub.utils._errors.RepositoryNotFoundError: 401 Client Error. (Request ID: Root=1-6432b193-63f16cd13cfc24fd7ce973a3) Repository Not Found for url: https://huggingface.co/api/models/model/simcse-chinese-roberta-wwm-ext.
Please make sure you specified the correct repo_id and repo_type.
If you are trying to access a private or gated repo, make sure you are authenticated.
Invalid username or password.

Traceback (most recent call last):
File "C:\Users\adria\AI\chatglm-6b\wenda-main\GLM6BAPI.py", line 149, in
import zhishiku
File "C:\Users\adria\AI\chatglm-6b\wenda-main\zhishiku.py", line 5, in
ix = storage.open_index()
File "C:\Users\adria\anaconda3\envs\wendaGLM\lib\site-packages\whoosh\filedb\filestore.py", line 176, in open_index
return indexclass(self, schema=schema, indexname=indexname)
File "C:\Users\adria\anaconda3\envs\wendaGLM\lib\site-packages\whoosh\index.py", line 421, in init
TOC.read(self.storage, self.indexname, schema=self._schema)
File "C:\Users\adria\anaconda3\envs\wendaGLM\lib\site-packages\whoosh\index.py", line 618, in read
raise EmptyIndexError("Index %r does not exist in %r"
whoosh.index.EmptyIndexError: Index 'MAIN' does not exist in FileStorage('sy')

不知道是不是环境出问题了？配置好好几次 都是一样的错误

最新的 settings.bat 不能运行！

1.glm60B已经在3090跑起来可以用了
2.在wenda里面也进行了路径替换
3.创建了txt目录，输了多行数据
4.执行脚本适合报错如下
5.求救作者我是哪里出问题了
glm模型地址 /home/hycan/HDD1/opt/zck/nlp/ChatGLM-6B/model
rwkv模型地址 model/RWKV-4-Raven-7B-v7-ChnEng-20230404-ctx2048.pth
rwkv模型参数 cuda fp16i8 *18+
日志记录 True
chunk_size 200
chunk_count 1
Traceback (most recent call last):
File "GLM6BAPI.py", line 140, in
import zhishiku
File "/home/hycan/HDD1/opt/zck/nlp/wenda/zhishiku.py", line 5, in
ix = storage.open_index()
File "/usr/local/anaconda3/lib/python3.8/site-packages/whoosh/filedb/filestore.py", line 176, in open_index
return indexclass(self, schema=schema, indexname=indexname)
File "/usr/local/anaconda3/lib/python3.8/site-packages/whoosh/index.py", line 421, in init
TOC.read(self.storage, self.indexname, schema=self._schema)
File "/usr/local/anaconda3/lib/python3.8/site-packages/whoosh/index.py", line 618, in read
raise EmptyIndexError("Index %r does not exist in %r"
whoosh.index.EmptyIndexError: Index 'MAIN' does not exist in FileStorage('sy')
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:08<00:00, 1.06s/it]
模型加载完成

有意pr

Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Exception in thread Thread-1 (load_model):
Traceback (most recent call last):
File "X:\wenda.7z\WPy64-31090\python-3.10.9.amd64\lib\threading.py", line 1016, in _bootstrap_inner
self.run()
File "X:\wenda.7z\WPy64-31090\python-3.10.9.amd64\lib\threading.py", line 953, in run
self._target(*self.args, **self.kwargs)
File "X:\wenda.7z\GLM6BAPI.py", line 144, in load_model
model = AutoModel.from_pretrained(glm_path, local_files_only=True, trust_remote_code=True)
File "X:\wenda.7z\WPy64-31090\python-3.10.9.amd64\lib\site-packages\transformers\models\auto\auto_factory.py", line 459, in from_pretrained
return model_class.from_pretrained(
File "X:\wenda.7z\WPy64-31090\python-3.10.9.amd64\lib\site-packages\transformers\modeling_utils.py", line 2362, in from_pretrained
model = cls(config, *model_args, **model_kwargs)
File "C:\Users\1/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py", line 940, in init
self.quantize(self.config.quantization_bit, self.config.quantization_embeddings, use_quantization_cache=True, empty_init=True)
File "C:\Users\1/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py", line 1262, in quantize
from .quantization import quantize, QuantizedEmbedding, QuantizedLinear, load_cpu_kernel
File "C:\Users\1/.cache\huggingface\modules\transformers_modules\local\quantization.py", line 13, in
from cpm_kernels.kernels.base import LazyKernelCModule, KernelFunction, round_up
File "X:\wenda.7z\WPy64-31090\python-3.10.9.amd64\lib\site-packages\cpm_kernels_init.py", line 1, in
from . import library
File "X:\wenda.7z\WPy64-31090\python-3.10.9.amd64\lib\site-packages\cpm_kernels\library_init.py", line 1, in
from . import nvrtc
File "X:\wenda.7z\WPy64-31090\python-3.10.9.amd64\lib\site-packages\cpm_kernels\library\nvrtc.py", line 5, in
nvrtc = Lib("nvrtc")
File "X:\wenda.7z\WPy64-31090\python-3.10.9.amd64\lib\site-packages\cpm_kernels\library\base.py", line 45, in init
lib_path = windows_find_lib(self.__name)
File "X:\wenda.7z\WPy64-31090\python-3.10.9.amd64\lib\site-packages\cpm_kernels\library\base.py", line 39, in windows_find_lib
return lookup_dll(lib_name)
File "X:\wenda.7z\WPy64-31090\python-3.10.9.amd64\lib\site-packages\cpm_kernels\library\base.py", line 16, in lookup_dll
for name in os.listdir(path):
NotADirectoryError: [WinError 267] 目录名称无效。: 'C:\Users\1\AppData\Local\Programs\Python\Python311\python.exe'
X:\wenda.7z\WPy64-31090\python-3.10.9.amd64\lib\site-packages\langchain\chains\conversational_retrieval\base.py:191: UserWarning: ChatVectorDBChain is deprecated - please use from langchain.chains import ConversationalRetrievalChain
warnings.warn(
:914: ImportWarning: _ImportRedirect.find_spec() not found; falling back to find_module()
serving on http://127.0.0.1:17860

系统: WSL2

1. 准备了一个空虚拟环境, 选用传统索引方式, 安装依赖requirements-sy.txt;
2. 运行run_data_processing.sh, 无问题;
3. 运行run_GLM6B.sh, 提示没有安装torch, 于是安装;
4. 运行run_GLM6B.sh, 报错RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())]

完整的报错输出如下. 这个错误我一直遇到, 不管是用传统索引还是用语义分割.

glm模型地址 model/chatglm-6b
rwkv模型地址 model/RWKV-4-Raven-7B-v7-ChnEng-20230404-ctx2048.pth
rwkv模型参数 cuda fp16
日志记录 True
知识库类型 s
LLM模型类型 glm6b
chunk_size 400
chunk_count 3
<frozen importlib._bootstrap>:1049: ImportWarning: _ImportRedirect.find_spec() not found; falling back to find_module()
serving on 0.0.0.0:17860 view at http://127.0.0.1:17860
<frozen importlib._bootstrap>:1049: ImportWarning: _ImportRedirect.find_spec() not found; falling back to find_module()
<frozen importlib._bootstrap>:1049: ImportWarning: _ImportRedirect.find_spec() not found; falling back to find_module()
<frozen importlib._bootstrap>:1049: ImportWarning: _ImportRedirect.find_spec() not found; falling back to find_module()
<frozen importlib._bootstrap>:1049: ImportWarning: _ImportRedirect.find_spec() not found; falling back to find_module()
<frozen importlib._bootstrap>:1049: ImportWarning: _ImportRedirect.find_spec() not found; falling back to find_module()
/home/wangfh5/anaconda3/envs/wenda/lib/python3.11/site-packages/jieba/analyse/tfidf.py:47: ResourceWarning: unclosed file <_io.BufferedReader name='/home/wangfh5/anaconda3/envs/wenda/lib/python3.11/site-packages/jieba/analyse/idf.txt'>
  content = open(new_idf_path, 'rb').read().decode('utf-8')
ResourceWarning: Enable tracemalloc to get the object allocation traceback
知识库加载完成
Explicitly passing a `revision` is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Exception in thread Thread-1 (load_model):
Traceback (most recent call last):
  File "/home/wangfh5/anaconda3/envs/wenda/lib/python3.11/threading.py", line 1038, in _bootstrap_inner
    self.run()
  File "/home/wangfh5/anaconda3/envs/wenda/lib/python3.11/threading.py", line 975, in run
    self._target(*self._args, **self._kwargs)
  File "/home/wangfh5/AIGC_projects/wenda/wenda.py", line 117, in load_model
    LLM.load_model()
  File "/home/wangfh5/AIGC_projects/wenda/plugins/llm_glm6b.py", line 25, in load_model
    tokenizer = AutoTokenizer.from_pretrained(settings.glm_path, local_files_only=True, trust_remote_code=True)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/wangfh5/anaconda3/envs/wenda/lib/python3.11/site-packages/transformers/models/auto/tokenization_auto.py", line 658, in from_pretrained
    return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/wangfh5/anaconda3/envs/wenda/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 1804, in from_pretrained
    return cls._from_pretrained(
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/wangfh5/anaconda3/envs/wenda/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 1959, in _from_pretrained
    tokenizer = cls(*init_inputs, **init_kwargs)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/wangfh5/.cache/huggingface/modules/transformers_modules/local/tokenization_chatglm.py", line 205, in __init__
    self.sp_tokenizer = SPTokenizer(vocab_file, num_image_tokens=num_image_tokens)
                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/wangfh5/.cache/huggingface/modules/transformers_modules/local/tokenization_chatglm.py", line 61, in __init__
    self.text_tokenizer = TextTokenizer(vocab_file)
                          ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/wangfh5/.cache/huggingface/modules/transformers_modules/local/tokenization_chatglm.py", line 22, in __init__
    self.sp.Load(model_path)
  File "/home/wangfh5/anaconda3/envs/wenda/lib/python3.11/site-packages/sentencepiece/__init__.py", line 905, in Load
    return self.LoadFromFile(model_file)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/wangfh5/anaconda3/envs/wenda/lib/python3.11/site-packages/sentencepiece/__init__.py", line 310, in LoadFromFile
    return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())]

windows10
cuda12
pytorch2.0.0
python3.10
已下载[simcse-chinese-roberta-wwm-ext并放在sentence-transformers\simcse-chinese-roberta-wwm-ext。并完整安装requirements.txt
修改了GLM6BAPI.py的138行model_path="D:/chatglm-6B-int4"（chatglm的绝对路径）
修改了model_name = "D:/Python/Python310/Lib/site-packages/sentence_transformers/simcse-chinese-roberta-wwm-ext"（simcse-chinese-roberta-wwm-ext的绝对路径）
运行“PS D:\Desktop\wenda-main> .\运行GLM6B.bat”
报错
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Traceback (most recent call last):
File "D:\Desktop\wenda-main\GLM6BAPI.py", line 162, in
vectorstore = FAISS.load_local('xw', embeddings=embeddings)
File "D:\Python\Python310\lib\site-packages\langchain\vectorstores\faiss.py", line 406, in load_local
index = faiss.read_index(str(path / "index.faiss"))
File "D:\Python\Python310\lib\site-packages\faiss\swigfaiss.py", line 9651, in read_index
return _swigfaiss.read_index(*args)
RuntimeError: Error in __cdecl faiss::FileIOReader::FileIOReader(const char *) at D:\a\faiss-wheels\faiss-wheels\faiss\faiss\impl\io.cpp:68: Error: 'f' failed: could not open xw\index.faiss for reading: No such file or directory
No compiled kernel found.
Compiling kernels : C:\Users\zx.cache\huggingface\modules\transformers_modules\local\quantization_kernels_parallel.c
Compiling gcc -O3 -fPIC -pthread -fopenmp -std=c99 C:\Users\zx.cache\huggingface\modules\transformers_modules\local\quantization_kernels_parallel.c -shared -o C:\Users\zx.cache\huggingface\modules\transformers_modules\local\quantization_kernels_parallel.so
'gcc' 不是内部或外部命令，也不是可运行的程序
或批处理文件。
Compile failed, using default cpu kernel code.
Compiling gcc -O3 -fPIC -std=c99 C:\Users\zx.cache\huggingface\modules\transformers_modules\local\quantization_kernels.c -shared -o C:\Users\zx.cache\huggingface\modules\transformers_modules\local\quantization_kernels.so
Kernels compiled : C:\Users\zx.cache\huggingface\modules\transformers_modules\local\quantization_kernels.so
Cannot load cpu kernel, don't use quantized model on cpu.
Using quantization cache
Applying quantization to glm layers
Exception ignored in: <module 'threading' from 'D:\Python\Python310\lib\threading.py'>
Traceback (most recent call last):
File "D:\Python\Python310\lib\threading.py", line 1567, in _shutdown
lock.acquire()
KeyboardInterrupt:

"Could not load dynamic library 'cudart64_110.dll';
文件是有的，还需要装啥？

辛苦作者，建议后续增加接入Stable Diffusion的API接口对接功能，类似Text generation webUI这个项目

RT
局域网远程访问ip+17860端口访问不了webui，想问问怎么做局域网部署

我使用的是[ChatGLM-6B]的官方模型，因为是6G显卡，所以加载模型的时候是通过修改参数（quantize(4)）让6G显卡跑起来的。
请问一下这个项目应该在哪里修改模型参数？
或者官方量化后的4-bit模型在哪里下载？我一直没找到。
先谢谢了

加载过程如下：

WebUI 端口号 17860
glm模型地址 ..\ChatGLM-6B\model
rwkv模型地址 ..\RWKV-4-Raven-7B-v7-ChnEng-20230404-ctx2048.pth
rwkv模型参数 cuda fp16i8 *18+
rwkv LoRA 微调启用: ""
日志记录 True
知识库类型 s
LLM模型类型 glm6b
chunk_size 200
chunk_count 3
serving on 0.0.0.0:17860 view at http://127.0.0.1:17860
D:\wenda4.10\WPy64-38100\python-3.8.10.amd64\lib\site-packages\jieba\analyse\tfidf.py:47: ResourceWarning: unclosed file <_io.BufferedReader name='D:\wenda4.10\WPy64-38100\python-3.8.10.amd64\lib\site-packages\jieba\analyse\idf.txt'>
content = open(new_idf_path, 'rb').read().decode('utf-8')
ResourceWarning: Enable tracemalloc to get the object allocation traceback
知识库加载完成
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
C:\Users\ASUS/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1229: DeprecationWarning: invalid escape sequence ?
["?", "？"],
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 8/8 [00:08<00:00, 1.11s/it]
glm int4量化中，如果已经是量化模型或不需要量化，不要开启
模型加载完成

127.0.0.1:你好
错误 'ChatGLMForConditionalGeneration' object has no attribute 'stream_chat' 'ChatGLMForConditionalGeneration' object has no attribute 'stream_chat'
glm模型地址 C:\ChatGLM_SERVER\model\chatglm-6b
embeddings模型地址 model\simcse-chinese-roberta-wwm-ext
vectorstore保存地址 xw
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Loading checkpoint shards: 12%|███████▏ | 1/8 [00:01<00:08, 1.26s/it]D:\AI_GLM\Wenda02\WPy64-31090\python-3.10.9.amd64\lib\site-packages\langchain\chains\conversational_retrieval\base.py:191: UserWarning: ChatVectorDBChain is deprecated - please use from langchain.chains import ConversationalRetrievalChain
warnings.warn(
:914: ImportWarning: _ImportRedirect.find_spec() not found; falling back to find_module()
serving on http://127.0.0.1:17860
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 8/8 [00:09<00:00, 1.19s/it]

使用的懒人包，目前只能127.0.0.0上使用，局域网访问该服务器，如何设定？

现在默认启动只能本机运行，我想内网的手机也能访问，是否有网络请求配置相关的参数设置？

UserWarning: ChatVectorDBChain is deprecated - please use from langchain.chains import ConversationalRetrievalChain
warnings.warn(
:914: ImportWarning: _ImportRedirect.find_spec() not found; falling back to find_module()User

能阅读pdf吗

感谢作者的付出，赛博菩萨。
一、问题背景：使用的新版的集成包，准备了一个txt文档，且下载好了“simcse-chinese-roberta-wwm-ext”放入models文件夹，想让其构建知识库。
二、问题描述：按照项目运行说明，运行"run_data_processing.bat"文件，出现如下编码格式报错信息：

embeddings模型地址 model\simcse-chinese-roberta-wwm-ext
vectorstore保存地址 xw
Traceback (most recent call last):
File "D:\pythonProject\wenda\gen_data.py", line 20, in
data = f.read()
File "D:\pythonProject\wenda\WPy64-31090\python-3.10.9.amd64\lib\codecs.py", line 322, in decode
(result, consumed) = self._buffer_decode(data, self.errors, final)
File "D:\pythonProject\wenda\WPy64-31090\python-3.10.9.amd64\lib\encodings\utf_16.py", line 61, in _buffer_decode
codecs.utf_16_ex_decode(input, errors, 0, final)
UnicodeDecodeError: 'utf-16-le' codec can't decode bytes in position 192-193: illegal UTF-16 surrogate

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\pythonProject\wenda\gen_data.py", line 23, in
data = f.read()
File "D:\pythonProject\wenda\WPy64-31090\python-3.10.9.amd64\lib\codecs.py", line 322, in decode
(result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xe8 in position 81: invalid continuation byte
请按任意键继续. . .

错误 expected scalar type Half but found Float expected scalar type Half but found Float
没有11G以上显存，无法确认原生fp16是否正常运行
windows10
cuda12
pytorch2.0.0
python3.10

怎么 联系你？

您好，因为我使用的是Ubuntu的系统，所以我将启动代码改为 PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:32 && python GLM6BAPI.py

webui可以正常使用，但是等待模型加载完（我看到nvidia-smi中有显存的使用）后，我提问发现跟模型未加载完的情况一样，
glm的回复都是三个.

请问我这个模型是否加载了？或者是我哪里设置的有问题

日志：

Explicitly passing a `revision` is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
<frozen importlib._bootstrap>:914: ImportWarning: _ImportRedirect.find_spec() not found; falling back to find_module()
serving on http://10.0.16.61:8502
Explicitly passing a `revision` is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a `revision` is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
/home/final/.cache/huggingface/modules/transformers_modules/THUDM/chatglm-6b/fdb7a601d8f8279806124542e11549bdd76f62f6/modeling_chatglm.py:1229: DeprecationWarning: invalid escape sequence '\?'
  ["\?", "？"],
<frozen importlib._bootstrap>:914: ImportWarning: _ImportRedirect.find_spec() not found; falling back to find_module()
Loading checkpoint shards: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:14<00:00,  1.75s/it]

其中：
我将现在代码修改为这个，因为我并没有找到代码中提到的 sentence-transformers/text2vec-base-chinese

model_name = "sentence-transformers/simcse-chinese-roberta-wwm-ext"

Exception in thread Thread-1:
Traceback (most recent call last):
File "E:\LLM\wenda\WPy64-38100\python-3.8.10.amd64\lib\threading.py", line 932, in _bootstrap_inner
self.run()
File "E:\LLM\wenda\WPy64-38100\python-3.8.10.amd64\lib\threading.py", line 870, in run
self._target(*self._args, **self._kwargs)
File "rwkvAPI.py", line 142, in load_model
from rwkv.model import RWKV # pip install rwkv
ModuleNotFoundError: No module named 'rwkv'

embeddings = HuggingFaceEmbeddings(model_name=model_name)
这一句报错，因为huggingface没登录，怎么改成本地已经下载的呀

发生异常: RepositoryNotFoundError
401 Client Error. (Request ID: Root=1-642c3974-240560a346fb2eb565ed790b)

Repository Not Found for url: https://huggingface.co/api/models/sentence-transformers/text2vec-base-chinese.
Please make sure you specified the correct repo_id and repo_type.
If you are trying to access a private or gated repo, make sure you are authenticated.
Invalid username or password.
requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/api/models/sentence-transformers/text2vec-base-chinese

The above exception was the direct cause of the following exception:

File "E:\AI模型\wenda-main\GLM6BAPI.py", line 152, in
embeddings = HuggingFaceEmbeddings(model_name=model_name)
huggingface_hub.utils._errors.RepositoryNotFoundError: 401 Client Error. (Request ID: Root=1-642c3974-240560a346fb2eb565ed790b)

Repository Not Found for url: https://huggingface.co/api/models/sentence-transformers/text2vec-base-chinese.
Please make sure you specified the correct repo_id and repo_type.
If you are trying to access a private or gated repo, make sure you are authenticated.
Invalid username or password.

我尝试使用colab运行此项目

from google.colab import drive
drive.mount('/content/drive')

%cd /content/drive/MyDrive/
!git clone https://github.com/l15y/wenda

# 安装依赖
%cd /content/drive/MyDrive/wenda
!pip install -r requirements.txt
%mkdir /content/drive/MyDrive/wenda/model
%cd /content/drive/MyDrive/wenda/model
!git lfs install
!git clone https://huggingface.co/THUDM/chatglm-6b-int4

%cd /content/drive/MyDrive/wenda
!chmod +x run_GLM6B.sh
!./run_GLM6B.sh

但是报错了

/content/drive/MyDrive/wenda
glm模型地址 model/chatglm-6b-int4
rwkv模型地址 model/RWKV-4-Raven-7B-v7-ChnEng-20230404-ctx2048.pth
rwkv模型参数 cuda fp16i8 *18+
日志记录 True
chunk_size 200
chunk_count 1
Traceback (most recent call last):
  File "/content/drive/MyDrive/wenda/GLM6BAPI.py", line 141, in <module>
    import zhishiku
  File "/content/drive/MyDrive/wenda/zhishiku.py", line 5, in <module>
    ix = storage.open_index()
  File "/usr/local/lib/python3.9/dist-packages/whoosh/filedb/filestore.py", line 176, in open_index
    return indexclass(self, schema=schema, indexname=indexname)
  File "/usr/local/lib/python3.9/dist-packages/whoosh/index.py", line 421, in __init__
    TOC.read(self.storage, self.indexname, schema=self._schema)
  File "/usr/local/lib/python3.9/dist-packages/whoosh/index.py", line 618, in read
    raise EmptyIndexError("Index %r does not exist in %r"
whoosh.index.EmptyIndexError: Index 'MAIN' does not exist in FileStorage('sy')
2023-04-08 11:35:16.730034: I tensorflow/core/util/port.cc:110] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2023-04-08 11:35:17.027958: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-04-08 11:35:18.109132: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Exception in thread Thread-1:
Traceback (most recent call last):
  File "/usr/lib/python3.9/threading.py", line 980, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.9/threading.py", line 917, in run
    self._target(*self._args, **self._kwargs)
  File "/content/drive/MyDrive/wenda/GLM6BAPI.py", line 130, in load_model
    from transformers import AutoModel, AutoTokenizer
  File "/usr/local/lib/python3.9/dist-packages/transformers/__init__.py", line 30, in <module>
    from . import dependency_versions_check
  File "/usr/local/lib/python3.9/dist-packages/transformers/dependency_versions_check.py", line 17, in <module>
    from .utils.versions import require_version, require_version_core
  File "/usr/local/lib/python3.9/dist-packages/transformers/utils/__init__.py", line 34, in <module>
    from .generic import (
  File "/usr/local/lib/python3.9/dist-packages/transformers/utils/generic.py", line 33, in <module>
    import tensorflow as tf
  File "/usr/local/lib/python3.9/dist-packages/tensorflow/__init__.py", line 51, in <module>
    from ._api.v2 import compat
  File "/usr/local/lib/python3.9/dist-packages/tensorflow/_api/v2/compat/__init__.py", line 37, in <module>
    from . import v1
  File "/usr/local/lib/python3.9/dist-packages/tensorflow/_api/v2/compat/v1/__init__.py", line 31, in <module>
    from . import compat
  File "/usr/local/lib/python3.9/dist-packages/tensorflow/_api/v2/compat/v1/compat/__init__.py", line 38, in <module>
    from . import v2
  File "/usr/local/lib/python3.9/dist-packages/tensorflow/_api/v2/compat/v1/compat/v2/__init__.py", line 28, in <module>
    from tensorflow._api.v2.compat.v2 import __internal__
  File "/usr/local/lib/python3.9/dist-packages/tensorflow/_api/v2/compat/v2/__init__.py", line 33, in <module>
    from . import compat
  File "/usr/local/lib/python3.9/dist-packages/tensorflow/_api/v2/compat/v2/compat/__init__.py", line 38, in <module>
    from . import v2
  File "/usr/local/lib/python3.9/dist-packages/tensorflow/_api/v2/compat/v2/compat/v2/__init__.py", line 332, in <module>
    from tensorboard.summary._tf import summary
  File "/usr/local/lib/python3.9/dist-packages/tensorboard/summary/__init__.py", line 22, in <module>
    from tensorboard.summary import v1  # noqa: F401
  File "/usr/local/lib/python3.9/dist-packages/tensorboard/summary/v1.py", line 23, in <module>
    from tensorboard.plugins.histogram import summary as _histogram_summary
  File "/usr/local/lib/python3.9/dist-packages/tensorboard/plugins/histogram/summary.py", line 35, in <module>
    from tensorboard.plugins.histogram import summary_v2
  File "/usr/local/lib/python3.9/dist-packages/tensorboard/plugins/histogram/summary_v2.py", line 35, in <module>
    from tensorboard.util import tensor_util
  File "/usr/local/lib/python3.9/dist-packages/tensorboard/util/tensor_util.py", line 20, in <module>
    from tensorboard.compat.tensorflow_stub import dtypes, compat, tensor_shape
  File "/usr/local/lib/python3.9/dist-packages/tensorboard/compat/tensorflow_stub/__init__.py", line 22, in <module>
    from .dtypes import as_dtype  # noqa
  File "/usr/local/lib/python3.9/dist-packages/tensorboard/compat/tensorflow_stub/dtypes.py", line 19, in <module>
    from . import pywrap_tensorflow
  File "/usr/local/lib/python3.9/dist-packages/tensorboard/compat/tensorflow_stub/pywrap_tensorflow.py", line 22, in <module>
    from .io import gfile
  File "/usr/local/lib/python3.9/dist-packages/tensorboard/compat/tensorflow_stub/io/__init__.py", line 17, in <module>
    from . import gfile  # noqa
  File "/usr/local/lib/python3.9/dist-packages/tensorboard/compat/tensorflow_stub/io/gfile.py", line 40, in <module>
    import fsspec
  File "/usr/local/lib/python3.9/dist-packages/fsspec/__init__.py", line 3, in <module>
    from . import _version, caching
  File "/usr/local/lib/python3.9/dist-packages/fsspec/caching.py", line 9, in <module>
    from concurrent.futures import ThreadPoolExecutor
  File "<frozen importlib._bootstrap>", line 1055, in _handle_fromlist
  File "/usr/lib/python3.9/concurrent/futures/__init__.py", line 49, in __getattr__
    from .thread import ThreadPoolExecutor as te
  File "/usr/lib/python3.9/concurrent/futures/thread.py", line 37, in <module>
    threading._register_atexit(_python_exit)
  File "/usr/lib/python3.9/threading.py", line 1414, in _register_atexit
    raise RuntimeError("can't register atexit after shutdown")
RuntimeError: can't register atexit after shutdown

Describe the bug
懒人包加载模型错误,

To Reproduce

1. 双击运行数据训练, 成功;
2. 双击运行模型, 失败

输出内容如下:

glm模型地址 model\chatglm-6b-int4
rwkv模型地址 ..\RWKV-4-Raven-7B-v7-ChnEng-20230404-ctx2048.pth
rwkv模型参数 cuda fp16i8 *18+
日志记录 True
知识库类型 s
chunk_size 200
chunk_count 3
serving on 0.0.0.0:17860 view at http://127.0.0.1:17860
D:\免安装软件\wenda\WPy64-38100\python-3.8.10.amd64\lib\site-packages\jieba\analyse\tfidf.py:47: ResourceWarning: unclosed file <_io.BufferedReader name='D:\\免安装软件\\wenda\\WPy64-38100\\python-3.8.10.amd64\\lib\\site-packages\\jieba\\analyse\\idf.txt'>
  content = open(new_idf_path, 'rb').read().decode('utf-8')
ResourceWarning: Enable tracemalloc to get the object allocation traceback
知识库加载完成
Explicitly passing a `revision` is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a `revision` is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a `revision` is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
C:\Users\Fohong Wang/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1229: DeprecationWarning: invalid escape sequence \?
  ["\?", "？"],
Symbol cudaLaunchKernel not found in C:\Program Files (x86)\NVIDIA Corporation\PhysX\Common\cudart64_65.dll
No compiled kernel found.
Compiling kernels : C:\Users\Fohong Wang\.cache\huggingface\modules\transformers_modules\local\quantization_kernels_parallel.c
Compiling gcc -O3 -fPIC -pthread -fopenmp -std=c99 C:\Users\Fohong Wang\.cache\huggingface\modules\transformers_modules\local\quantization_kernels_parallel.c -shared -o C:\Users\Fohong Wang\.cache\huggingface\modules\transformers_modules\local\quantization_kernels_parallel.so
gcc: error: C:\Users\Fohong: No such file or directory
gcc: error: Wang\.cache\huggingface\modules\transformers_modules\local\quantization_kernels_parallel.c: No such file or directory
gcc: error: Wang\.cache\huggingface\modules\transformers_modules\local\quantization_kernels_parallel.so: No such file or directory
gcc: fatal error: no input files
compilation terminated.
Compile failed, using default cpu kernel code.
Compiling gcc -O3 -fPIC -std=c99 C:\Users\Fohong Wang\.cache\huggingface\modules\transformers_modules\local\quantization_kernels.c -shared -o C:\Users\Fohong Wang\.cache\huggingface\modules\transformers_modules\local\quantization_kernels.so
gcc: error: C:\Users\Fohong: No such file or directory
gcc: error: Wang\.cache\huggingface\modules\transformers_modules\local\quantization_kernels.c: No such file or directory
gcc: error: Wang\.cache\huggingface\modules\transformers_modules\local\quantization_kernels.so: No such file or directory
gcc: fatal error: no input files
compilation terminated.
Kernels compiled : C:\Users\Fohong Wang\.cache\huggingface\modules\transformers_modules\local\quantization_kernels.so
Cannot load cpu kernel, don't use quantized model on cpu.
Using quantization cache
Applying quantization to glm layers
模型加载完成

这里报错似乎是因为我的用户名有空格, 路径又没有加""导致命令错误, 于是我自己手动把这两个文件编译好了, 但再次运行还是同样的错误.

如此之外, cmd 还弹出了如下警告.

请问如何解决？