run ./llm_demo ../../../Qwen2.5-0.5B-Instruct-MNN/config.json prompt.txt error

[xtanitfy]

(base) yd@yd-Default-string:~/workspace/MNN/MNN/build$ ./llm_demo ../../../Qwen2.5-0.5B-Instruct-MNN/config.json prompt.txt
Can't open file:/sys/devices/system/cpu/cpufreq/schedutil/affected_cpus
CPU Group: [ 2 0 3 1 ], 1332800 - 2415700
The device supports: i8sdot:0, fp16:0, i8mm: 0, sve2: 0
config path is ../../../Qwen2.5-0.5B-Instruct-MNN/config.json
Can't open file:tmp/mnn_cachefile.bin
Load Cache file error.
load tokenizer
tokenizer_type = 3
load tokenizer Done
load ../../../Qwen2.5-0.5B-Instruct-MNN/llm.mnn ... Invalidate buffer to create MNN Module
Load Module Done!
段错误 (核心已转储)

[Qxinyu]

这个模型是从huggingface下载得到的吗，看起来是模型的问题。

[xtanitfy]

用的魔塔的https://modelscope.cn/models/MNN/Qwen2.5-0.5B-Instruct-MNN
照这个步骤做的

[Qxinyu]

看下文件大小正常吗，有可能是没有下载完整。