.

requirements.txt

@@ -22,37 +22,28 @@ sentencepiece
 tensorboard
 tqdm
 wandb
-exllama
 
 # bitsandbytes
-bitsandbytes==0.41.1; platform_system != "Windows"
-https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
+bitsandbytes==0.41.1
 
 # AutoGPTQ
-https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
-https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu117-cp310-cp310-linux_x86_64.whl
 
 # ExLlama
-https://github.com/jllllll/exllama/releases/download/0.0.14/exllama-0.0.14+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
-https://github.com/jllllll/exllama/releases/download/0.0.14/exllama-0.0.14+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/jllllll/exllama/releases/download/0.0.14/exllama-0.0.14+cu117-cp310-cp310-linux_x86_64.whl
 
 # llama-cpp-python without GPU support
-llama-cpp-python==0.1.83; platform_system != "Windows"
-https://github.com/abetlen/llama-cpp-python/releases/download/v0.1.83/llama_cpp_python-0.1.83-cp310-cp310-win_amd64.whl; platform_system == "Windows"
+llama-cpp-python==0.1.83
 
 # llama-cpp-python with CUDA support
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.1.83+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.1.83+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.1.83+cu117-cp310-cp310-linux_x86_64.whl
 
 # llama-cpp-python with GGML support
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python_ggml-0.1.78+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python_ggml-0.1.78+cpuavx2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_ggml_cuda-0.1.78+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_ggml_cuda-0.1.78+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python_ggml-0.1.78+cpuavx2-cp310-cp310-linux_x86_64.whl
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_ggml_cuda-0.1.78+cu117-cp310-cp310-linux_x86_64.whl
 
 # GPTQ-for-LLaMa
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-linux_x86_64.whl
 
 # ctransformers
 https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX2/ctransformers-0.2.25+cu117-py3-none-any.whl