报错
mszjaas opened this issue · comments
提交前必须检查以下项目
- 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。
- 由于相关依赖频繁更新，请确保按照Wiki中的相关步骤执行
- 我已阅读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
- 第三方插件问题：例如llama.cpp、text-generation-webui、LlamaChat等，同时建议到对应的项目中查找解决方案
- 模型正确性检查：务必检查模型的SHA256.md，模型不对的情况下无法保证效果和正常运行
问题类型
模型推理
基础模型
Alpaca-7B
操作系统
Linux
详细描述问题
正常merge了模型，运行下面代码开server，报错
python3 /home/mszjaas/lib/Chinese-LLaMA-Alpaca/scripts/openai_server_demo/openai_api_server.py --base_model ~/models/7b_model --only_cpu
依赖情况（代码类问题务必提供）
# 请在此处粘贴依赖情况
运行日志或截图
[mszjaas@n1 Chinese-LLaMA-Alpaca]$ python3 scripts/openai_server_demo/openai_api_server.py --base_model /home/mszjaas/models/alpaca-combined-hf --only_cpu
Xformers is not installed correctly. If you want to use memory_efficient_attention use the following command to install Xformers
pip install xformers.
USE_MEM_EFF_ATTENTION: False
STORE_KV_BEFORE_ROPE: False
Apply NTK scaling with ALPHA=1.0
/home/mszjaas/.local/lib/python3.11/site-packages/torch/cuda/init.py:107: UserWarning: CUDA initialization: The NVIDIA driver on your system is too old (found version 10010). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver. (Triggered internally at ../c10/cuda/CUDAFunctions.cpp:109.)
return torch._C._cuda_getDeviceCount() > 0
Loading checkpoint shards: 100%|██████████████████████████████████████| 3/3 [03:19<00:00, 66.37s/it]
Vocab of the base model: 49953
Vocab of the tokenizer: 49953
2024-01-11 20:12:12,399 - INFO - Started server process [29923]
2024-01-11 20:12:12,630 - INFO - Waiting for application startup.
2024-01-11 20:12:12,631 - INFO - Application startup complete.
2024-01-11 20:12:12,632 - INFO - Uvicorn running on http://0.0.0.0:19327 (Press CTRL+C to quit)
2024-01-11 20:15:01,296 - INFO - 127.0.0.1:40768 - "POST /v1/chat/completions HTTP/1.1" 500
2024-01-11 20:15:01,297 - ERROR - Exception in ASGI application
Traceback (most recent call last):
File "/home/mszjaas/.local/lib/python3.11/site-packages/uvicorn/protocols/http/h11_impl.py", line 408, in run_asgi
result = await app( # type: ignore[func-returns-value]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mszjaas/.local/lib/python3.11/site-packages/uvicorn/middleware/proxy_headers.py", line 84, in call
return await self.app(scope, receive, send)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mszjaas/.local/lib/python3.11/site-packages/fastapi/applications.py", line 1054, in call
await super().call(scope, receive, send)
File "/home/mszjaas/.local/lib/python3.11/site-packages/starlette/applications.py", line 116, in call
await self.middleware_stack(scope, receive, send)
File "/home/mszjaas/.local/lib/python3.11/site-packages/starlette/middleware/errors.py", line 186, in call
raise exc
File "/home/mszjaas/.local/lib/python3.11/site-packages/starlette/middleware/errors.py", line 164, in call
await self.app(scope, receive, _send)
File "/home/mszjaas/.local/lib/python3.11/site-packages/starlette/middleware/exceptions.py", line 62, in call
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
File "/home/mszjaas/.local/lib/python3.11/site-packages/starlette/_exception_handler.py", line 55, in wrapped_app
raise exc
File "/home/mszjaas/.local/lib/python3.11/site-packages/starlette/_exception_handler.py", line 44, in wrapped_app
await app(scope, receive, sender)
File "/home/mszjaas/.local/lib/python3.11/site-packages/starlette/routing.py", line 746, in call
await route.handle(scope, receive, send)
File "/home/mszjaas/.local/lib/python3.11/site-packages/starlette/routing.py", line 288, in handle
await self.app(scope, receive, send)
File "/home/mszjaas/.local/lib/python3.11/site-packages/starlette/routing.py", line 75, in app
await wrap_app_handling_exceptions(app, request)(scope, receive, send)
File "/home/mszjaas/.local/lib/python3.11/site-packages/starlette/_exception_handler.py", line 55, in wrapped_app
raise exc
File "/home/mszjaas/.local/lib/python3.11/site-packages/starlette/_exception_handler.py", line 44, in wrapped_app
await app(scope, receive, sender)
File "/home/mszjaas/.local/lib/python3.11/site-packages/starlette/routing.py", line 70, in app
response = await func(request)
^^^^^^^^^^^^^^^^^^^
File "/home/mszjaas/.local/lib/python3.11/site-packages/fastapi/routing.py", line 299, in app
raise e
File "/home/mszjaas/.local/lib/python3.11/site-packages/fastapi/routing.py", line 294, in app
raw_response = await run_endpoint_function(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mszjaas/.local/lib/python3.11/site-packages/fastapi/routing.py", line 191, in run_endpoint_function
return await dependant.call(**values)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mszjaas/lib/Chinese-LLaMA-Alpaca/scripts/openai_server_demo/openai_api_server.py", line 182, in create_chat_completion
output = predict(
^^^^^^^^
File "/home/mszjaas/lib/Chinese-LLaMA-Alpaca/scripts/openai_server_demo/openai_api_server.py", line 136, in predict
generation_output = model.generate(
^^^^^^^^^^^^^^^
File "/home/mszjaas/.local/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/home/mszjaas/.local/lib/python3.11/site-packages/transformers/generation/utils.py", line 1764, in generate
return self.sample(
^^^^^^^^^^^^
File "/home/mszjaas/.local/lib/python3.11/site-packages/transformers/generation/utils.py", line 2861, in sample
outputs = self(
^^^^^
File "/home/mszjaas/.local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mszjaas/.local/lib/python3.11/site-packages/transformers/models/llama/modeling_llama.py", line 1181, in forward
outputs = self.model(
^^^^^^^^^^^
File "/home/mszjaas/.local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mszjaas/.local/lib/python3.11/site-packages/transformers/models/llama/modeling_llama.py", line 1068, in forward
layer_outputs = decoder_layer(
^^^^^^^^^^^^^^
File "/home/mszjaas/.local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mszjaas/.local/lib/python3.11/site-packages/transformers/models/llama/modeling_llama.py", line 796, in forward
hidden_states, self_attn_weights, present_key_value = self.self_attn(
^^^^^^^^^^^^^^^
File "/home/mszjaas/.local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mszjaas/lib/Chinese-LLaMA-Alpaca/scripts/openai_server_demo/patches.py", line 49, in xformers_forward
kv_seq_len += past_key_value[0].shape[-2]
~~~~~~~~~~~~~~^^^
File "/home/mszjaas/.local/lib/python3.11/site-packages/transformers/cache_utils.py", line 78, in getitem
raise KeyError(f"Cache only has {len(self)} layers, attempted to access layer with index {layer_idx}")
KeyError: 'Cache only has 0 layers, attempted to access layer with index 0'
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.
Closing the issue, since no updates observed. Feel free to re-open if you need any further assistance.