.

requirements.txt

@@ -1,7 +1,7 @@
 aiofiles==23.1.0
 fastapi==0.95.2
-gradio_client==0.2.5
-gradio==3.33.1
+gradio_client>=0.2.5
+gradio>=3.33.1
 
 accelerate==0.22.*
 colorama
@@ -11,11 +11,11 @@ markdown
 numpy==1.24
 optimum==1.12.0
 pandas
-peft==0.5.*
+peft>=0.5.*
 Pillow>=9.5.0
 pyyaml
 requests
-safetensors==0.3.2
+safetensors
 transformers==4.32.*
 scipy
 sentencepiece
@@ -26,24 +26,11 @@ wandb
 # bitsandbytes
 bitsandbytes==0.41.1
 
-# AutoGPTQ
-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-linux_x86_64.whl
+exllama
 
 # llama-cpp-python without GPU support
 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-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-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-linux_x86_64.whl
-
 # ctransformers
 https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX2/ctransformers-0.2.25+cu117-py3-none-any.whl