M1芯片上运行出现报错🥲 #6
Comments
|
解决了吗，还没实验mac本地运行，如果成功了欢迎PR分享一份心得文档 ～ |
|
没解决, 用gpt修改完运行是不报错了, 跑了15分钟一个字没蹦出来就关了,需要的话我可以把修改完的代码贴出来 |
|
可能需要用 llama.cpp 或者 ollama方案
…---原始邮件---
发件人: ***@***.***>
发送时间: 2024年4月22日(周一) 上午10:35
收件人: ***@***.***>;
抄送: "Ke ***@***.******@***.***>;
主题: Re: [CrazyBoyM/llama3-Chinese-chat] M1芯片上运行出现报错🥲 (Issue #6)
没解决, 用gpt修改完运行是不报错了, 跑了15分钟一个字没蹦出来就关了,需要的话我可以把修改完的代码贴出来
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
|
copy 我试试去 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
测试版本1: 3.9.6
测试版本2: 3.12.0
都是在user输入后报错
终端运行:
Traceback (most recent call last): File "/Users/pckxin/Desktop/LLama3CH/main.py", line 175, in <module> main() File "/Users/pckxin/Desktop/LLama3CH/main.py", line 153, in main outputs = model.generate( ^^^^^^^^^^^^^^^ File "/Users/pckxin/Desktop/LLama3CH/.venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/Users/pckxin/Desktop/LLama3CH/.venv/lib/python3.12/site-packages/transformers/generation/utils.py", line 1622, in generate result = self._sample( ^^^^^^^^^^^^^ File "/Users/pckxin/Desktop/LLama3CH/.venv/lib/python3.12/site-packages/transformers/generation/utils.py", line 2847, in _sample unfinished_sequences = unfinished_sequences & ~stopping_criteria(input_ids, scores) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/pckxin/Desktop/LLama3CH/.venv/lib/python3.12/site-packages/transformers/generation/stopping_criteria.py", line 158, in __call__ is_done = is_done | criteria(input_ids, scores, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/pckxin/Desktop/LLama3CH/.venv/lib/python3.12/site-packages/transformers/generation/stopping_criteria.py", line 149, in __call__ is_done = torch.isin(input_ids[:, -1], self.eos_token_id.to(input_ids.device)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ NotImplementedError: The operator 'aten::isin.Tensor_Tensor_out' is not currently implemented for the MPS device. If you want this op to be added in priority during the prototype phase of this feature, please comment on https://github.com/pytorch/pytorch/issues/77764. As a temporary fix, you can set the environment variablePYTORCH_ENABLE_MPS_FALLBACK=1to use the CPU as a fallback for this op. WARNING: this will be slower than running natively on MPS.网页运行:
File "/Users/pckxin/Desktop/LLama3CH/.venv/lib/python3.12/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 584, in _run_script exec(code, module.__dict__) File "/Users/pckxin/Desktop/LLama3CH/deploy/web_streamlit_for_v1.py", line 307, in <module> main(model_name_or_path, adapter_name_or_path) File "/Users/pckxin/Desktop/LLama3CH/deploy/web_streamlit_for_v1.py", line 281, in main for cur_response in generate_interactive( File "/Users/pckxin/Desktop/LLama3CH/.venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 35, in generator_context response = gen.send(None) ^^^^^^^^^^^^^^ File "/Users/pckxin/Desktop/LLama3CH/deploy/web_streamlit_for_v1.py", line 51, in generate_interactive inputs[k] = v.cuda() ^^^^^^^^ File "/Users/pckxin/Desktop/LLama3CH/.venv/lib/python3.12/site-packages/torch/cuda/__init__.py", line 293, in _lazy_init raise AssertionError("Torch not compiled with CUDA enabled")The text was updated successfully, but these errors were encountered: