Open xiaoma1990-git opened 7 months ago
我昨天使用MiniChat-2-3B也遇到了,48G内存,3060显卡,win11 wsl2。今天换成Qwen-1_8B-Chat,LLM启动成功了,正在测试中
NVIDIA GeForce RTX 2080 Ti 我的显卡是这个 另外还有T4的 好像只能弄1.8B 或者3B的模型 硬件限制。。
Qwen-1_8B-Chat可以运行,但是对话有问题, bash ./run.sh -c local -i 0 -b hf -m Qwen-1_8B-Chat -t qwen-7b-qanything。
3B要求显存得有10G以上
我 2080ti 22G 没跑起来 3B模型............
Qwen-1_8B-Chat
48g显存运行3B的那个模型也没起来么? 我是2080ti 22g的启动失败了
是否已有关于该错误的issue或讨论? | Is there an existing issue / discussion for this?
该问题是否在FAQ中有解答? | Is there an existing answer for this in FAQ?
当前行为 | Current Behavior
No response
期望行为 | Expected Behavior
No response
运行环境 | Environment
QAnything日志 | QAnything logs
qanything-container-local | ������ LLM ��������������������������� /workspace/qanything_local/logs/debug_logs/fastchat_logs/fschat_model_worker_7801.log ���������������Error... qanything-container-local | 2024-04-07 15:54:44 | ERROR | stderr | tokenizer.Load(self.vocab_file) qanything-container-local | 2024-04-07 15:54:44 | ERROR | stderr | File "/usr/local/lib/python3.10/dist-packages/sentencepiece/init.py", line 905, in Load qanything-container-local | 2024-04-07 15:54:44 | ERROR | stderr | return self.LoadFromFile(model_file) qanything-container-local | 2024-04-07 15:54:44 | ERROR | stderr | File "/usr/local/lib/python3.10/dist-packages/sentencepiece/init.py", line 310, in LoadFromFile qanything-container-local | 2024-04-07 15:54:44 | ERROR | stderr | return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg) qanything-container-local | 2024-04-07 15:54:44 | ERROR | stderr | RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())]
复现方法 | Steps To Reproduce
No response
备注 | Anything else?
No response