qwen.cpp
qwen.cpp copied to clipboard
QwenLM
C++ implementation of Qwen-LM
[ 98%] Built target flags_parse [ 99%] Linking CXX static library lib/libqwen.a [ 99%] Built target qwen [ 99%] Building CXX object CMakeFiles/main.dir/main.cpp.o [ 99%] Building CXX object CMakeFiles/_C.dir/qwen_pybind.cpp.o In...
execute python qwen_cpp/convert.py -i /Qwen-7B-Chat -t q4_0 -o qwen7b-ggml.bin false: AttributeError: 'QWenConfig' object has no attribute 'padded_vocab_size'
It raise Import Error when execute `python3 qwen_cpp/convert.py xxx` command raise ImportError( ImportError: This modeling file requires the following packages that were not found in your environment: kernels, flash_attn. Run...
root@a:~/qwen/qwen.cpp/qwen_cpp# python3 convert.py -i /root/qwen/Qwen1.5-1.8B -t q4_0 -o qwen1_8b.bin Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Traceback (most recent...
我用gradio架构构建了一个前端界面，现在希望通过qwen-cpp进行cpu推理，并和前端界面进行交互通信，请问有什么办法吗
我使用的源模型为hf上下载的Qwen/Qwen-1_8B-Chat，显示模型权重也就不到4g  但为什么我使用```python3 qwen_cpp/convert.py -i Qwen/Qwen-1-8B-Chat -t f32 -o qwen1-8b-ggml.bin``` 生成的权重文件反而增大到了6g多呢？
## 报错: ```text [ 98%] Linking CXX static library ../../../../lib/libabsl_flags_usage.a [ 98%] Built target flags_usage [ 99%] Building CXX object third_party/abseil-cpp/absl/flags/CMakeFiles/flags_parse.dir/parse.cc.o /usr/bin/ld: lib/libre2.a(re2.cc.o): relocation R_X86_64_TPOFF32 against symbol `_ZN3re25hooks7contextE' can not...
运行命令：pip install -U qwen-cpp，请问这个是什么问题？ 报错如下： Collecting qwen-cpp Using cached https://pypi.tuna.tsinghua.edu.cn/packages/a4/76/61e947717636072018ce25a5929af05b0e47538a564cc0c3298935b38a49/qwen-cpp-0.1.3.tar.gz (2.9 MB) Installing build dependencies ... done Getting requirements to build wheel ... done Installing backend dependencies ... done Preparing...
